© 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. 30862
    Prev
    Next
    INDEX
    Explanations

    analog tachometer

    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
    Blan
    -0.08
    å®ļäºİ
    -0.08
    è¿ĻäºĽäºĭæĥħ
    -0.06
    ahre
    -0.06
    .CSS
    -0.06
    unar
    -0.06
    uja
    -0.06
    /wiki
    -0.06
    angat
    -0.06
    åĤĢ
    -0.06
    POSITIVE LOGITS
    åħ¬èĭ±
    0.08
    פק
    0.07
    ä¸įåı¯ç¼ºå°ij
    0.07
     getLocation
    0.06
    mium
    0.06
    ä¸įåĢĴ
    0.06
    odz
    0.06
    аниÑĨ
    0.06
    iated
    0.06
    idious
    0.06
    Activations Density 0.752%

    No Known Activations