© 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. 25995
    Prev
    Next
    INDEX
    Explanations

    engine/drive

    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
     Covers
    -0.06
     Tender
    -0.06
     Fully
    -0.06
     Larger
    -0.06
     SMALL
    -0.06
    DO
    -0.06
     Tiger
    -0.06
     Scaffold
    -0.06
    .Logger
    -0.06
     navegador
    -0.06
    POSITIVE LOGITS
     xuống
    0.07
     comes
    0.07
    חינוך
    0.07
    UE
    0.06
     exercício
    0.06
     combined
    0.06
    ら
    0.06
    getClass
    0.06
    _trial
    0.06
    비
    0.06
    Activations Density 0.019%

    No Known Activations