© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 23453
    Prev
    Next
    INDEX
    Explanations

    legal cases

    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
     countryCode
    -0.07
    .setWidth
    -0.07
    .qt
    -0.07
    🍑
    -0.07
     таким
    -0.07
     shampoo
    -0.07
     sock
    -0.07
    Geom
    -0.07
    这个词
    -0.07
     complementary
    -0.06
    POSITIVE LOGITS
    냬
    0.07
    urances
    0.06
     خط
    0.06
    赃
    0.06
     Widow
    0.06
    _numer
    0.06
     say
    0.06
    建档立
    0.06
    .info
    0.06
    皛
    0.06
    Activations Density 0.006%

    No Known Activations