© 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. 41000
    Prev
    Next
    INDEX
    Explanations

    against attractive prices / this / one / the / which / rust / an / obscene / Joe / executive

    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
    并èĮĤ
    -0.11
    ioc
    -0.09
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.09
    Been
    -0.08
    ë¦Ħ
    -0.08
    abeth
    -0.08
    othi
    -0.08
    ilton
    -0.08
    ؤ
    -0.08
    вок
    -0.08
    POSITIVE LOGITS
    /off
    0.09
    ering
    0.08
    enticate
    0.08
    /by
    0.08
    /out
    0.08
     ÑģебÑı
    0.08
    s
    0.08
    woord
    0.07
    ../../
    0.07
    /from
    0.07
    Activations Density 0.033%

    No Known Activations