© 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. 10979
    Prev
    Next
    INDEX
    Explanations

    code structure begin tokens

    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
    ои
    -0.08
    ä¸Ģ空
    -0.08
    ohn
    -0.08
    Ãłn
    -0.08
    满满çļĦ
    -0.07
    éļĪ
    -0.07
    заÑĢ
    -0.07
    isman
    -0.07
    SError
    -0.07
    aland
    -0.07
    POSITIVE LOGITS
    ãģĺãĤģãģ¦
    0.07
    缸éĢ¢
    0.07
    ìĹ°
    0.06
    TeX
    0.06
    begin
    0.06
    åĦª
    0.06
    azia
    0.06
    åŁºéĩijé¡¹çĽ®
    0.06
    astique
    0.06
    åħļå·¥å§Ķ
    0.06
    Activations Density 0.005%

    No Known Activations