© 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. 19-RESID-POST-AA
    11. 70977
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LIABLE
    -0.08
    嗖
    -0.08
    .↵↵↵
    -0.08
    ﴘ
    -0.08
     unin
    -0.07
     ważne
    -0.07
     מגיב
    -0.07
    高尔夫
    -0.07
    。。↵↵
    -0.07
     נולד
    -0.07
    POSITIVE LOGITS
     Об
    0.08
     ';'
    0.08
    /off
    0.07
    bern
    0.07
    ':'
    0.07
    HTTPHeader
    0.07
    经济
    0.07
     Cipher
    0.07
    cliffe
    0.06
     Arbeits
    0.06
    Activations Density 0.100%

    No Known Activations