© 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. 42611
    Prev
    Next
    INDEX
    Explanations

    +

    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
    natural
    -0.07
     MAN
    -0.07
    Maybe
    -0.07
     MAD
    -0.07
     المسلحة
    -0.06
    市人大
    -0.06
    .period
    -0.06
    (Main
    -0.06
    撮
    -0.06
    市委
    -0.06
    POSITIVE LOGITS
     altri
    0.08
     stesso
    0.08
     ella
    0.07
     necessário
    0.07
     eliminar
    0.07
     questa
    0.07
     ogni
    0.07
    esk
    0.07
     יחסי
    0.07
     llevar
    0.07
    Activations Density 0.006%

    No Known Activations