© 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. 37976
    Prev
    Next
    INDEX
    Explanations

    color, build, code, or song phrases

    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
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.08
    åIJįæĢĿ
    -0.08
    æĻĵ举
    -0.08
    管å±Ģ
    -0.08
    åħ¨æĸĩæķ°æį®åºĵ
    -0.08
    stery
    -0.07
    çĽijå§Ķ
    -0.07
    å°±æĪIJ为
    -0.07
    elop
    -0.07
    ä¸Ĭè¯ģ
    -0.07
    POSITIVE LOGITS
     Febbraio
    0.07
    iggs
    0.06
    两个åŃĹ
    0.06
    aug
    0.06
     respectively
    0.06
    ãĥĭãĥ¥
    0.06
    äºĮåŃĹ
    0.06
    æľ«
    0.06
    äºĪ
    0.06
    auc
    0.06
    Activations Density 0.024%

    No Known Activations