© 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. 62601
    Prev
    Next
    INDEX
    Explanations

    actions and representations

    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
    queira
    -0.06
    nav
    -0.06
    并å¤Ħ
    -0.06
    lang
    -0.06
    .firstChild
    -0.06
     dioxide
    -0.06
    åѦèĢĮ
    -0.06
    iger
    -0.06
    osaur
    -0.06
    ä½Ļç¯ĩ
    -0.06
    POSITIVE LOGITS
    æĸ¹å¼ıæĺ¯
    0.08
    cht
    0.08
    ekan
    0.08
    æĸ¹å¼ı为
    0.08
    äck
    0.08
    rch
    0.08
    uoj
    0.08
    elf
    0.08
    füh
    0.07
    è¿ĩçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations