© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    function 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
    æĢ§æĪĸ
    -0.07
    ä¸Ģå¼łå¼ł
    -0.06
    ä¸Ģéģĵéģĵ
    -0.06
    lade
    -0.06
    ä¼´
    -0.06
    èĪį
    -0.06
    _impl
    -0.06
    æĢ»ä¸įèĥ½
    -0.06
    éģĵåı£
    -0.06
    orough
    -0.06
    POSITIVE LOGITS
    åı¯çĶ¨äºİ
    0.08
    IST
    0.07
    allel
    0.07
    IRM
    0.07
    à¹Ģà¸Ķีย
    0.07
    代人
    0.07
    WithValue
    0.07
    çī¹åĪ«æĺ¯å¯¹
    0.07
    çĶ¨å®ĥ
    0.07
    gres
    0.07
    Activations Density 0.097%

    No Known Activations