© 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. 39859
    Prev
    Next
    INDEX
    Explanations

    bottom half

    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
    ëĮĢë¡ľ
    -0.07
    ppi
    -0.07
    ania
    -0.07
    ä»ĭ
    -0.06
    endir
    -0.06
    ä½ĥ
    -0.06
     thá»ijng
    -0.06
    游åѦ
    -0.06
    hen
    -0.06
    off
    -0.06
    POSITIVE LOGITS
    erton
    0.08
    éĻħ
    0.08
    INC
    0.07
    åħĪæĿ¥
    0.07
    inoa
    0.07
    LOW
    0.07
    æŃ£ç¡®å¤ĦçIJĨ
    0.07
    åĪĩå®ŀåģļ好
    0.07
    è¡£èįī
    0.06
    YTE
    0.06
    Activations Density 0.012%

    No Known Activations