© 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. 89634
    Prev
    Next
    INDEX
    Explanations

    "s"

    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
     Input
    -0.08
    amo
    -0.07
    (light
    -0.07
    dim
    -0.07
     Wish
    -0.07
    .rabbit
    -0.07
    Bill
    -0.07
    kich
    -0.07
    (File
    -0.07
    class
    -0.06
    POSITIVE LOGITS
    ,
    0.08
    ة
    0.07
    ubah
    0.07
    根源
    0.07
    뛴
    0.07
    햊
    0.07
    /svg
    0.07
     bahwa
    0.07
    建军
    0.07
    а
    0.07
    Activations Density 2.190%

    No Known Activations