© 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. 27286
    Prev
    Next
    INDEX
    Explanations

    source code files and licenses

    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
    鞫
    -0.07
     clo
    -0.06
    יעה
    -0.06
    돐
    -0.06
    ȅ
    -0.06
     thẳng
    -0.06
     само
    -0.06
    <boolean
    -0.06
    edula
    -0.06
    Moved
    -0.06
    POSITIVE LOGITS
     XIII
    0.08
     blast
    0.07
    izador
    0.07
     пыта
    0.07
    рус
    0.07
    actor
    0.07
    Things
    0.07
     Poz
    0.07
    browser
    0.07
     IBM
    0.07
    Activations Density 0.391%

    No Known Activations