© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18029
    Prev
    Next
    INDEX
    Explanations

    time, health, and places

    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
    ows
    -0.08
    antara
    -0.08
    æĹ©çŁ¥éģĵ
    -0.08
    iau
    -0.08
    ssi
    -0.08
    otos
    -0.08
    구ëĤĺ
    -0.08
    оÑģÑĤÑĢе
    -0.08
    \/\/
    -0.07
    åĪ©äºļ
    -0.07
    POSITIVE LOGITS
     trans
    0.06
    2
    0.06
    [
    0.06
    <|box_end|>
    0.06
    0.06
    3
    0.06
    åħµåĻ¨
    0.06
    ãģ®ãģĵãģ¨
    0.06
    g
    0.05
     [
    0.05
    Activations Density 0.459%

    No Known Activations