© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46646
    Prev
    Next
    INDEX
    Explanations

    table column names

    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
    èĩĬ
    -0.08
    ieg
    -0.07
    人æĹł
    -0.07
    ä¹Łåı¯èĥ½æĺ¯
    -0.07
    éĿ
    -0.07
    æľ¬æĸĩæĿ¥èĩª
    -0.07
    iskus
    -0.07
    hausen
    -0.06
    quito
    -0.06
    _Tag
    -0.06
    POSITIVE LOGITS
    å¤ĩ注
    0.08
    onex
    0.07
    isphere
    0.07
    åıĬéĻĦåĬł
    0.07
    £¼
    0.07
    ",'
    0.07
    aji
    0.07
    rophe
    0.06
    ","+
    0.06
     devastated
    0.06
    Activations Density 0.151%

    No Known Activations