© 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. 63291
    Prev
    Next
    INDEX
    Explanations

    recurrence relation

    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
    enticate
    -0.11
    缸è¾ħ缸æĪIJ
    -0.10
    æĸ°åĬłåĿ¡
    -0.09
    ths
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    jenigen
    -0.08
    оÑģÑĤо
    -0.08
    ectores
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    POSITIVE LOGITS
    witz
    0.08
    Į
    0.08
    IndexOf
    0.08
    eves
    0.07
    äre
    0.07
    istar
    0.07
    edy
    0.07
    /rec
    0.07
    åı¯å¾ª
    0.07
    ären
    0.06
    Activations Density 0.005%

    No Known Activations