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. 15-RESID-POST-AA
    6. 120958
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﯔ
    -0.08
    stateProvider
    -0.08
    有期徒刑
    -0.07
    缂
    -0.07
    zerbai
    -0.07
    济宁
    -0.07
    ﰮ
    -0.07
    تض
    -0.07
    浐
    -0.07
    缜
    -0.07
    POSITIVE LOGITS
     Đề
    0.07
     doubles
    0.07
    ؛
    0.07
     subtitle
    0.07
    (surface
    0.06
    Overall
    0.06
     vot
    0.06
     mMap
    0.06
    null
    0.06
    _rows
    0.06
    Activations Density 8.706%

    No Known Activations