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. 11-RESID-POST-AA
    6. 41401
    Prev
    Next
    INDEX
    Explanations

    email format

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inant
    -0.08
     зрения
    -0.08
    竞技
    -0.08
    ライブ
    -0.07
    發揮
    -0.07
    _hand
    -0.07
    卫生间
    -0.07
     Club
    -0.07
     brig
    -0.07
     Highlands
    -0.07
    POSITIVE LOGITS
     ili
    0.08
    XHR
    0.07
    .dao
    0.07
    עריכת
    0.07
     בגלל
    0.07
    رتبط
    0.07
     проблем
    0.07
     najczę
    0.06
    ngrx
    0.06
     להגיע
    0.06
    Activations Density 0.001%

    No Known Activations