© 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. 47496
    Prev
    Next
    INDEX
    Explanations

    residual quantity or condition

    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
     ulang
    -0.11
    æĸ°åĬłåĿ¡
    -0.09
    åĬłæĭ¿å¤§
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    imum
    -0.09
    iquement
    -0.09
    cid
    -0.09
    enticate
    -0.08
    aits
    -0.08
    althy
    -0.08
    POSITIVE LOGITS
    æĹłåĩł
    0.08
    еÑĨ
    0.08
    ä¸įå¤ļçļĦ
    0.07
    uns
    0.07
    à§įব
    0.06
    at
    0.06
    ager
    0.06
     Kampung
    0.06
    é¦
    0.06
    ä¸ĭæĿ¥çļĦ
    0.06
    Activations Density 0.030%

    No Known Activations