© 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. 38365
    Prev
    Next
    INDEX
    Explanations

    viktualienmarkt

    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
    åįĹè¡Ĺ
    -0.08
     Domen
    -0.07
    apk
    -0.07
    åIJĪæĪIJ
    -0.07
    _cached
    -0.07
    [${
    -0.07
    åIJĪæĪIJçļĦ
    -0.07
    ãģ²
    -0.06
    çĶŁäº§æĢ»åĢ¼
    -0.06
     pré
    -0.06
    POSITIVE LOGITS
    ington
    0.08
    _BINARY
    0.08
    TURE
    0.07
    pons
    0.07
    inton
    0.07
    _stuff
    0.07
    ä»»åĬ³
    0.07
    ëĤ©
    0.07
     fullname
    0.06
    äºĶ彩
    0.06
    Activations Density 0.028%

    No Known Activations