© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    special characters followed by numbers or currency

    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
    ale
    -0.07
    èĤ¥å¤§
    -0.07
    ier
    -0.07
    iae
    -0.07
    aim
    -0.07
    VL
    -0.06
    iat
    -0.06
    alm
    -0.06
    ANG
    -0.06
     jr
    -0.06
    POSITIVE LOGITS
    æĻ¨æĬ¥
    0.08
    ailand
    0.08
    çļĦ缸åħ³ä¿¡æģ¯
    0.08
    Ïīμα
    0.07
    _dispatcher
    0.07
    (dispatch
    0.07
    queta
    0.07
     Bok
    0.07
    idend
    0.07
    eddar
    0.07
    Activations Density 0.130%

    No Known Activations