© 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. 20382
    Prev
    Next
    INDEX
    Explanations

    mechanical connections and shafts

    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
    以åıĬå¦Ĥä½ķ
    -0.08
    为满足
    -0.07
     banh
    -0.06
     quen
    -0.06
    éĥ¨ç»ıçIJĨ
    -0.06
     Äijiá»ĥn
    -0.06
     "["
    -0.06
    ako
    -0.06
    ÙĤÙģ
    -0.06
    unist
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.12
    æĪĸèĢħ缴æİ¥
    0.08
    ramework
    0.07
    ombat
    0.07
    кÑĢе
    0.07
    dale
    0.07
    ÑıÑģÑĮ
    0.07
    áĢĦáĢ·áĢº
    0.07
    è¶ĬãģĹ
    0.07
    دÙĦ
    0.07
    Activations Density 0.165%

    No Known Activations