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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 70528
    Prev
    Next
    INDEX
    Explanations

    Programming

    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
    metrical
    -0.07
    .changed
    -0.07
    הפוך
    -0.07
    atu
    -0.07
     Himself
    -0.07
    nombre
    -0.06
    >Type
    -0.06
    $content
    -0.06
    原件
    -0.06
     mesmo
    -0.06
    POSITIVE LOGITS
     launching
    0.07
     arma
    0.07
     offenders
    0.07
    favorite
    0.07
     ATTR
    0.07
    Saga
    0.07
    ()));↵
    0.07
    volume
    0.06
    沈阳
    0.06
    同事们
    0.06
    Activations Density 0.098%

    No Known Activations