© 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. 39999
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs and formulas

    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
     vers
    -0.07
    sig
    -0.07
     cookie
    -0.07
    ivar
    -0.07
    ãĤ¯ãĥĪ
    -0.07
    _tbl
    -0.07
    äºĭåĭĻæīĢ
    -0.07
    对åIJĦç§į
    -0.07
    ISMATCH
    -0.07
    оÑĢий
    -0.06
    POSITIVE LOGITS
    èĭ¥èĥ½
    0.11
    å¦Ĥæŀľèĥ½
    0.11
    åħ³éĶ®åľ¨äºİ
    0.09
     hinges
    0.09
    åħ³éĶ®æĺ¯
    0.09
    åıªè¦ģèĥ½
    0.09
    èĥ½åIJ¦
    0.09
    å¦Ĥæŀľèĥ½å¤Ł
    0.08
    好ä¸į好
    0.08
    æĪij们éľĢè¦ģ
    0.08
    Activations Density 0.056%

    No Known Activations