© 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. 30692
    Prev
    Next
    INDEX
    Explanations

    microchip

    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
    inga
    -0.09
    tida
    -0.07
    fia
    -0.07
    akaan
    -0.07
    ados
    -0.07
    tidos
    -0.07
    adena
    -0.07
    idan
    -0.07
    bill
    -0.07
    vus
    -0.07
    POSITIVE LOGITS
    èĢĮä¸Ķæĺ¯
    0.10
    èĢĮä¸Ķè¿ĺæĺ¯
    0.10
    ç§°ä½ľ
    0.07
    ä½Ĩä¸įæĺ¯
    0.07
    èĢĮä¸Ķæľī
    0.07
    èĢĮä¸Ķ
    0.07
     whose
    0.07
    åij½åIJį为
    0.07
    åIJĹ
    0.07
    æİĴåIJį第
    0.06
    Activations Density 0.108%

    No Known Activations