© 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. 15045
    Prev
    Next
    INDEX
    Explanations

    numeric characters and code syntax

    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
    æĿ¡
    -0.08
    ERTO
    -0.08
    elui
    -0.07
    大åĪ©
    -0.07
    tdown
    -0.07
    ORT
    -0.07
    ä¸ĭæ²ī
    -0.07
    æĹłå¿Į
    -0.07
    orial
    -0.07
    åįİå±±
    -0.07
    POSITIVE LOGITS
    oney
    0.07
    ycin
    0.07
    Ñģев
    0.07
    sept
    0.07
    æ°¸
    0.07
    ital
    0.06
    åħ¨å¤©
    0.06
    æ³ķå®ļ代表人为
    0.06
    çĸ¤
    0.06
    çĥĺ
    0.06
    Activations Density 0.006%

    No Known Activations