© 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. 28321
    Prev
    Next
    INDEX
    Explanations

    code and english text boundaries

    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
     unsus
    -0.07
    åįĥ
    -0.06
    avan
    -0.06
    è®¤çľŁå®ĮæĪIJ
    -0.06
    ä¹Łæĺ¯æľĢ
    -0.06
    enez
    -0.06
    urin
    -0.06
    亡
    -0.06
    ymax
    -0.06
    oogle
    -0.06
    POSITIVE LOGITS
    çĻ»å½ķæŁ¥çľĭ
    0.08
    ivière
    0.08
    nyi
    0.08
    ayos
    0.08
    代ä¹ĭ
    0.08
    äºĨåĩºæĿ¥
    0.07
    pu
    0.07
    ÑĦиÑı
    0.07
    าย
    0.07
    éĩĮåİ»
    0.07
    Activations Density 0.029%

    No Known Activations