© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    mobilization and phenotypes

    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
    tsky
    -0.08
    缮å®ī
    -0.07
    çĤİ
    -0.07
    Ð¢ÐŁ
    -0.07
    _PARSE
    -0.07
    Vectorizer
    -0.07
    /graphql
    -0.07
    dze
    -0.06
     châm
    -0.06
    wers
    -0.06
    POSITIVE LOGITS
    é¹Ĭ
    0.07
    redict
    0.07
    说ä¸į
    0.07
    éĽģ
    0.07
    óf
    0.07
    è¦ĸ
    0.06
    æ´ŀ
    0.06
    ising
    0.06
    å°ij主
    0.06
    .nasa
    0.06
    Activations Density 0.897%

    No Known Activations