© 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. 9911
    Prev
    Next
    INDEX
    Explanations

    Chinese and English words

    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
    rastructure
    -0.08
    /or
    -0.08
    E
    -0.07
    /of
    -0.07
    bidden
    -0.07
    thew
    -0.06
    T
    -0.06
    ystal
    -0.06
    O
    -0.06
    htable
    -0.06
    POSITIVE LOGITS
    jenigen
    0.12
    orem
    0.11
    notated
    0.10
    人æ°ijåħ±åĴĮåĽ½
    0.09
    htags
    0.08
    ¾
    0.08
    ़
    0.08
     rajav
    0.08
    -Za
    0.08
    ãģ¯ãĤĬ
    0.08
    Activations Density 0.037%

    No Known Activations