© 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. 4261
    Prev
    Next
    INDEX
    Explanations

    people arriving from elsewhere

    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
    @student
    -0.08
    ToJson
    -0.07
    agini
    -0.07
     gegr
    -0.07
    å¿ĥå¾Ĺ
    -0.06
    产éĩı
    -0.06
    åĩºå£°
    -0.06
    åIJįå±±
    -0.06
    åĩºåĩ»
    -0.06
    åĩºéĿ¢
    -0.06
    POSITIVE LOGITS
    è¿ĽæĿ¥çļĦ
    0.18
    å¤ĸæĿ¥
    0.17
    è¿ĽæĿ¥
    0.17
     incoming
    0.16
    æĿ¥èĩª
    0.16
    æĺ¯æĿ¥èĩª
    0.16
     influx
    0.15
    æĿ¥çļĦ
    0.15
    æĿ¥çļĦæŶåĢĻ
    0.15
    éĢ²ä¾Ĩ
    0.15
    Activations Density 0.678%

    No Known Activations