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. 130054
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    unicip
    -0.07
    盍
    -0.07
     labelText
    -0.06
     roś
    -0.06
    .LayoutControlItem
    -0.06
    玱
    -0.06
     gal
    -0.06
     vestib
    -0.06
     Gib
    -0.06
     Cardiff
    -0.06
    POSITIVE LOGITS
    rokes
    0.08
     implant
    0.07
    アイテム
    0.07
    refund
    0.07
    rients
    0.07
    相关政策
    0.07
    *np
    0.07
    Subtitle
    0.07
    ependency
    0.07
    _tweets
    0.07
    Activations Density 0.000%

    No Known Activations