© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    function declarations / definitions

    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
    summ
    -0.08
    lobber
    -0.07
    aval
    -0.07
    åĩºå¤´
    -0.07
    å¾ĹåĬĽ
    -0.06
    amá
    -0.06
    autore
    -0.06
    aufs
    -0.06
    ually
    -0.06
    REAT
    -0.06
    POSITIVE LOGITS
    nten
    0.07
    andra
    0.07
    éĹ
    0.07
    lick
    0.07
    äºīåģļ
    0.07
    eks
    0.07
    tır
    0.07
    iola
    0.06
    ãĥįãĤ¹
    0.06
    hoff
    0.06
    Activations Density 0.031%

    No Known Activations