© 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. 26357
    Prev
    Next
    INDEX
    Explanations

    log messages or code comments

    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
    ouis
    -0.08
    engu
    -0.07
    ïs
    -0.07
    mates
    -0.06
    رÙĬÙĦ
    -0.06
    ç«ĭçļĦ
    -0.06
     prize
    -0.06
    pay
    -0.06
    CanBe
    -0.06
     Amat
    -0.06
    POSITIVE LOGITS
    ç»Īäºİåı¯ä»¥
    0.08
    åĩ«
    0.08
    éģĵè¿ľ
    0.08
    _FMT
    0.08
    gev
    0.08
     getpid
    0.08
    à¤Ĺत
    0.08
    ISTI
    0.07
    ONA
    0.07
    bine
    0.07
    Activations Density 0.052%

    No Known Activations