© 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. 38817
    Prev
    Next
    INDEX
    Explanations

    percent and scale notations

    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
    uet
    -0.07
    éĺµåľ°
    -0.07
    eid
    -0.07
    sv
    -0.07
    åIJĮæł·æĺ¯
    -0.07
     Auftritt
    -0.07
    åħ¸ç¤¼
    -0.07
    ä¸įæģ¯
    -0.07
    _specific
    -0.07
    庵
    -0.07
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.08
    /reference
    0.07
    بØŃ
    0.07
    (reference
    0.07
    parseFloat
    0.07
     Nug
    0.07
    -parse
    0.07
    áte
    0.07
    -reference
    0.07
    baseline
    0.07
    Activations Density 0.020%

    No Known Activations