© 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. 15638
    Prev
    Next
    INDEX
    Explanations

    following let statements

    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
    almaz
    -0.07
    eliac
    -0.07
    è¾»
    -0.07
    ÙĨب
    -0.07
    pool
    -0.07
    inger
    -0.07
    _CONF
    -0.07
    ertas
    -0.07
    eryl
    -0.07
     @[
    -0.06
    POSITIVE LOGITS
    ç¬Ļ
    0.07
    jú
    0.07
    ForObject
    0.07
    hés
    0.07
    èĪįå¾Ĺ
    0.07
    .ObjectId
    0.07
     finally
    0.07
    ìĪĺìĿĺ
    0.06
    weis
    0.06
    æıļ
    0.06
    Activations Density 0.010%

    No Known Activations