© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    . and ,

    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
    iesa
    -0.07
    edly
    -0.07
    ÑģÑı
    -0.07
    åIJĮä¸Ĭ
    -0.07
    lant
    -0.07
    æ¶Īå¤±åľ¨
    -0.06
    prit
    -0.06
    imbus
    -0.06
    imet
    -0.06
    odos
    -0.06
    POSITIVE LOGITS
    uxe
    0.07
    rokes
    0.07
    bject
    0.07
    绾ç»İ
    0.07
    åħ¶çľŁå®ŀæĢ§
    0.07
    ALI
    0.07
    -errors
    0.07
    igli
    0.07
    ä½ij
    0.07
    å¦Ĥæŀľåı¯ä»¥
    0.07
    Activations Density 0.011%

    No Known Activations