© 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. 29656
    Prev
    Next
    INDEX
    Explanations

    converting to a format

    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
    åķĨæłĩä¿¡æģ¯
    -0.08
    ä¸į以
    -0.07
    кÑĥмÑĥлÑı
    -0.07
    ç¿Ķ
    -0.06
    æī¶
    -0.06
    åŁºæľ¬
    -0.06
    èĢĮçŁ¥
    -0.06
    rather
    -0.06
    æĺ¯ä¸Ģå¹´
    -0.06
    å®ļåIJij
    -0.06
    POSITIVE LOGITS
    compatible
    0.10
    -compatible
    0.08
     compatible
    0.08
    Executable
    0.08
    è¿ĺå¿ħé¡»
    0.08
    å®ŀæĸ½æĸ¹æ¡Ī
    0.08
    format
    0.08
    Compatible
    0.08
     format
    0.07
    porter
    0.07
    Activations Density 0.128%

    No Known Activations