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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24523
    Prev
    Next
    INDEX
    Explanations

    up

    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
    atre
    -0.07
     porter
    -0.07
    ($('#
    -0.07
    )↵↵↵↵
    -0.07
    tle
    -0.07
    堇
    -0.06
    一批
    -0.06
    /
    -0.06
    淑
    -0.06
    rol
    -0.06
    POSITIVE LOGITS
    Oops
    0.07
    经销
    0.07
    南海网
    0.07
     approvals
    0.07
    _direction
    0.07
     fals
    0.07
    dsa
    0.07
    𝘢
    0.07
     disponibles
    0.07
    مشا
    0.07
    Activations Density 0.005%

    No Known Activations