© 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. 38089
    Prev
    Next
    INDEX
    Explanations

    custom fitness programsbackup retention dayssubscribers gain abilityhuge additionprogram that teams

    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
    kert
    -0.08
    ductive
    -0.08
    pped
    -0.07
    ëĤĺë§Ī
    -0.07
    genden
    -0.07
    licer
    -0.07
    exas
    -0.07
    <tool_response>
    -0.07
    vende
    -0.07
    errer
    -0.07
    POSITIVE LOGITS
    orem
    0.11
    oret
    0.09
    oretical
    0.09
    åIJĮä¸Ĭ
    0.09
    æĸ°åĬłåĿ¡
    0.09
     infatti
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    neath
    0.07
    åĬłæĭ¿å¤§
    0.07
    Activations Density 0.055%

    No Known Activations