© 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. 15957
    Prev
    Next
    INDEX
    Explanations

    code/technical data

    np_max-act · gemini-2.0-flash

    underscore-separated identifiers (snake_case names and underscored paths/fields) in code and config text.

    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
     Evidence
    -0.07
    了一口
    -0.07
    underscore
    -0.06
    燠
    -0.06
     Firmware
    -0.06
     brow
    -0.06
    救命
    -0.06
     belle
    -0.06
     pourquoi
    -0.06
     Dez
    -0.06
    POSITIVE LOGITS
    1
    0.13
     of
    0.11
    2
    0.08
    ↵
    0.08
    .↵
    0.08
     for
    0.08
     in
    0.08
    ↵↵
    0.08
    0
    0.08
    的
    0.08
    Activations Density 7.382%

    No Known Activations