© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25079
    Prev
    Next
    INDEX
    Explanations

    injective or surjective functions

    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
    翼翼
    -0.09
     miscellaneous
    -0.07
    è´´æģ¯
    -0.07
    延年
    -0.07
    tery
    -0.07
    coes
    -0.07
    recur
    -0.07
    defgroup
    -0.07
     recurse
    -0.07
    ç³»åĪĹ产åĵģ
    -0.07
    POSITIVE LOGITS
    ukat
    0.08
    Domains
    0.07
    éĩľ
    0.07
    jek
    0.07
     khắp
    0.07
    éĴĪ对
    0.07
    填满
    0.07
    éĴĪ对æĢ§
    0.07
    éĴĪ对æĢ§çļĦ
    0.07
    rof
    0.07
    Activations Density 0.002%

    No Known Activations