Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59370
    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
    قصر
    -0.07
    .setImage
    -0.07
    subtype
    -0.07
     używa
    -0.07
    这就是
    -0.07
    ,file
    -0.07
    ập
    -0.06
    dateFormat
    -0.06
     DAMAGES
    -0.06
     generar
    -0.06
    POSITIVE LOGITS
    足
    0.07
    .connections
    0.07
     reasonable
    0.06
    הול
    0.06
     newArr
    0.06
    intérieur
    0.06
    ثمان
    0.06
    이고
    0.06
    🖏
    0.06
    _DIPSETTING
    0.06
    Activations Density 0.003%

    No Known Activations