© 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. 23132
    Prev
    Next
    INDEX
    Explanations

    scrutiny, look, thoroughly, idea, time, browse, submitted

    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
    éģŃ
    -0.08
    æŦ
    -0.07
    urian
    -0.07
    _INLINE
    -0.06
    ared
    -0.06
    ssize
    -0.06
    доб
    -0.06
    vd
    -0.06
    æĢ»ä½ĵä¸Ĭ
    -0.06
     dispersed
    -0.06
    POSITIVE LOGITS
    js
    0.07
    auch
    0.07
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.07
    ilters
    0.07
    并举
    0.07
    aser
    0.07
    æĹ¢èĥ½
    0.07
    GY
    0.06
    æ¯ıä¸ĢæŃ¥
    0.06
    paque
    0.06
    Activations Density 0.001%

    No Known Activations