© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 71458
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash

    The neuron detects explicit instructions or metadata asking for a specific structured output format (especially JSON) and related formatting tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.12
    ，
    -0.10
    和
    -0.10
    .↵↵
    -0.09
    ());↵
    -0.08
    )↵↵
    -0.08
    。
    -0.08
    。↵↵
    -0.08
    ,↵
    -0.08
    );↵
    -0.08
    POSITIVE LOGITS
    3
    0.06
    /he
    0.06
    actual
    0.06
    حداث
    0.06
    替换
    0.06
     Evolution
    0.06
     таблиц
    0.05
    ектив
    0.05
    liśmy
    0.05
    깢
    0.05
    Activations Density 38.152%

    No Known Activations