© 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. 92625
    Prev
    Next
    INDEX
    Explanations

    toddler

    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
     wyś
    -0.07
     imageURL
    -0.07
    digital
    -0.07
    歅
    -0.07
    经
    -0.07
     <!--[
    -0.07
    高尔
    -0.07
     Biography
    -0.07
     denial
    -0.07
     alignSelf
    -0.06
    POSITIVE LOGITS
     toddler
    0.08
     Kardashian
    0.08
    ced
    0.08
    _TCP
    0.07
    のだ
    0.07
     concussion
    0.07
     Babies
    0.07
     successfully
    0.07
    çı
    0.07
    中に
    0.07
    Activations Density 0.002%

    No Known Activations