© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    Defendant, Lem, k, w, 3

    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
    itzer
    -0.08
    ÙĦÙħاÙĨ
    -0.07
     nÃłn
    -0.07
    opp
    -0.07
     resp
    -0.06
    ::_
    -0.06
    unate
    -0.06
    imin
    -0.06
     unk
    -0.06
    irk
    -0.06
    POSITIVE LOGITS
    ä¸ĩ家
    0.07
     ï½¢
    0.07
     Nationwide
    0.07
    жÑĮ
    0.07
    åįĥ家ä¸ĩæĪ·
    0.07
    æĪijçļĦçľĭæ³ķ
    0.07
    romo
    0.07
    ExceptionHandler
    0.07
    å¿ĺæİī
    0.07
    大æīĵ
    0.07
    Activations Density 0.001%

    No Known Activations