© 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. 4422
    Prev
    Next
    INDEX
    Explanations

    mathematical expression components

    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
    ilty
    -0.08
    èİ·èµŀ
    -0.08
    PTR
    -0.07
    PLAIN
    -0.07
    PPER
    -0.07
    isson
    -0.06
    ENZE
    -0.06
    kson
    -0.06
    æ³ķéĻ¢
    -0.06
    toa
    -0.06
    POSITIVE LOGITS
    boro
    0.07
    éĥijéĩį声æĺİ
    0.07
    /watch
    0.07
    andel
    0.07
    èĶļ
    0.07
    artes
    0.07
    backs
    0.07
    åľ¨çº¿éĺħ读
    0.07
    .watch
    0.07
    yster
    0.07
    Activations Density 0.017%

    No Known Activations