Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1738
    Prev
    Next
    INDEX
    Explanations

    structured

    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
    illisecond
    -0.08
    ﮣ
    -0.07
    getY
    -0.07
     mM
    -0.06
     scm
    -0.06
    phoon
    -0.06
     AMC
    -0.06
    ooky
    -0.06
    pthread
    -0.06
     IReadOnly
    -0.06
    POSITIVE LOGITS
    叁
    0.08
     Restaurants
    0.08
    _space
    0.07
    makers
    0.07
     wines
    0.07
    Export
    0.07
     Benefits
    0.07
     mess
    0.06
     helped
    0.06
                                                                                     
    0.06
    Activations Density 0.003%

    No Known Activations