© 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. 15-RESID-POST-AA
    11. 26526
    Prev
    Next
    INDEX
    Explanations

    initial

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wholes
    -0.07
     hect
    -0.07
     spraw
    -0.07
     Benz
    -0.06
     Peyton
    -0.06
     hour
    -0.06
    riv
    -0.06
    сет
    -0.06
    מבנה
    -0.06
    slave
    -0.06
    POSITIVE LOGITS
    偓
    0.07
     receptors
    0.07
    )"
    0.07
    cka
    0.07
    .em
    0.07
     geen
    0.07
     כא
    0.07
    Dataset
    0.06
    .Navigator
    0.06
    生物学
    0.06
    Activations Density 0.058%

    No Known Activations