© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28485
    Prev
    Next
    INDEX
    Explanations

    `(*` or `(` then `t`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.10
    es
    -0.08
    h
    -0.08
    ered
    -0.08
    hart
    -0.07
    à¥įड
    -0.07
    o
    -0.07
    ой
    -0.07
    ÑĥдаÑĢ
    -0.07
    heden
    -0.07
    POSITIVE LOGITS
    esseract
    0.16
    aylor
    0.14
    iffany
    0.14
    oulouse
    0.14
    ornado
    0.13
    warzys
    0.13
    imesteps
    0.12
    gether
    0.12
    deauna
    0.12
    ting
    0.12
    Activations Density 0.036%

    No Known Activations