© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22810
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or units

    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
    omat
    -0.07
     ÑģобÑģÑĤвенно
    -0.06
    alyzed
    -0.06
    ?",
    -0.06
    enor
    -0.06
    ');//
    -0.06
    æĴ°æĸĩ
    -0.06
    éķ¿åº¦çļĦ
    -0.06
    alian
    -0.06
    ?”,
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.08
    zb
    0.08
    uton
    0.07
    ãģĭãģĴ
    0.07
    è·Įå®ķ
    0.07
    urst
    0.07
    tre
    0.07
    irt
    0.07
    asanya
    0.07
    ãģİ
    0.07
    Activations Density 0.160%

    No Known Activations