© 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. 16779
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
     заÑĢа
    -0.08
    usso
    -0.07
    iso
    -0.07
    足ä¸įåĩº
    -0.07
    ulkan
    -0.07
    è½¼
    -0.07
    ¾¸
    -0.07
    uten
    -0.07
    ç¾İ好
    -0.07
    raÄĩ
    -0.07
    POSITIVE LOGITS
    ç¼ĵ
    0.08
    çĻ½çİī
    0.07
    æĹłçĹĽ
    0.07
    éal
    0.07
    æĪijçļĦè¯Ŀ
    0.07
    NotExist
    0.06
    bÃŃ
    0.06
    空
    0.06
    ogg
    0.06
     penal
    0.06
    Activations Density 0.011%

    No Known Activations