© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 43828
    Prev
    Next
    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash

    chat-style message delimiters and role headers that mark the start or end of user/assistant turns.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imid
    -0.07
     Pract
    -0.07
    .require
    -0.07
     Prem
    -0.07
     Occup
    -0.06
    _MED
    -0.06
     Dual
    -0.06
    _ARGS
    -0.06
     optimize
    -0.06
    楚
    -0.06
    POSITIVE LOGITS
    字体
    0.07
    Po
    0.07
     البيان
    0.07
    +$
    0.07
     бумаг
    0.07
    SourceType
    0.07
     closes
    0.07
    SerializedName
    0.07
    𝔷
    0.07
     새로
    0.07
    Activations Density 0.069%

    No Known Activations