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. 25153
    Prev
    Next
    INDEX
    Explanations

    om

    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
    _bel
    -0.07
    .VAL
    -0.07
    เสร
    -0.07
     erh
    -0.07
     pione
    -0.07
     behold
    -0.06
    哎
    -0.06
    热血传奇
    -0.06
    接手
    -0.06
    为导向
    -0.06
    POSITIVE LOGITS
    (strip
    0.07
    海军
    0.07
    ивать
    0.07
    inctions
    0.07
    俟
    0.07
     Ginny
    0.07
     учет
    0.07
     LAN
    0.07
    <int
    0.07
    谕
    0.07
    Activations Density 0.001%

    No Known Activations