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. 75453
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
     site
    -0.08
    ǔ
    -0.07
    Input
    -0.07
    new
    -0.07
     view
    -0.07
    tres
    -0.07
     View
    -0.07
    hog
    -0.07
    演练
    -0.07
    ﲒ
    -0.07
    POSITIVE LOGITS
    برشلون
    0.08
    _CE
    0.08
    镯
    0.08
     percentage
    0.08
     практичес
    0.08
     있었
    0.07
     affirmative
    0.07
     niekt
    0.07
    _percentage
    0.07
    然而
    0.07
    Activations Density 0.009%

    No Known Activations