© 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. 28004
    Prev
    Next
    INDEX
    Explanations

    if, whereas, but

    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
    _BGR
    -0.08
    /rs
    -0.08
    edir
    -0.07
    veill
    -0.07
    azon
    -0.07
     ÐŁÑĢоÑģмоÑĤÑĢов
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.07
    upy
    -0.07
    OGO
    -0.07
    /bit
    -0.07
    POSITIVE LOGITS
    æīĢ以
    0.08
     so
    0.07
     vs
    0.07
    ä¸įè¿ĩ
    0.07
     Anyway
    0.07
    æīĢ以çİ°åľ¨
    0.07
    æīĢ以æĪij
    0.07
     bumped
    0.06
    æīĢ以对
    0.06
    æĽ´
    0.06
    Activations Density 0.419%

    No Known Activations