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. 36579
    Prev
    Next
    INDEX
    Explanations

    code

    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
     UIWindow
    -0.08
    奉献
    -0.08
    食用
    -0.07
    箕
    -0.07
    电价
    -0.07
    环境卫生
    -0.07
    蛊
    -0.07
    㹦
    -0.06
     Opinion
    -0.06
    泣
    -0.06
    POSITIVE LOGITS
    都有自己
    0.07
     Quarterly
    0.06
     boards
    0.06
     aument
    0.06
    verts
    0.06
     possibile
    0.06
     nameof
    0.06
    Authorities
    0.06
    ϭ
    0.06
    中国队
    0.06
    Activations Density 0.006%

    No Known Activations