© 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. 1661
    Prev
    Next
    INDEX
    Explanations

    color specification

    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
     «
    -0.07
    aros
    -0.07
    ([{
    -0.06
    个头
    -0.06
    positor
    -0.06
    gel
    -0.06
    schirm
    -0.06
    abor
    -0.06
     imp
    -0.06
    æ´¥
    -0.06
    POSITIVE LOGITS
    <tool_response>
    0.08
    /callback
    0.08
    aler
    0.07
    rlen
    0.07
    ennie
    0.07
    estim
    0.07
    综
    0.07
    asher
    0.07
    è¿Ļä¸ī个
    0.07
    æ°´ä¸Ń
    0.07
    Activations Density 0.443%

    No Known Activations