© 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. 29902
    Prev
    Next
    INDEX
    Explanations

    pigeon

    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
    sver
    -0.09
    rieve
    -0.08
     Wandel
    -0.07
    并ä¸įç®Ĺ
    -0.07
    è¿Ľç¨ĭä¸Ń
    -0.07
     ì½ĶìĬ¤
    -0.07
    ÙĬع
    -0.07
    å®īå¸Ĥ
    -0.07
    abyrinth
    -0.07
    ordio
    -0.07
    POSITIVE LOGITS
     Empty
    0.07
     empty
    0.07
     NumberOf
    0.07
     pigeon
    0.07
    -empty
    0.07
    unen
    0.07
    jum
    0.07
    bern
    0.07
    æĭ¥æĮ¤
    0.07
     cram
    0.07
    Activations Density 0.001%

    No Known Activations