© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    network, vitamin, iterate, leaked, cancer

    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
    ÙĩاÙĨ
    -0.07
    ulier
    -0.07
    ãĥİãĥ³
    -0.07
    äºĮ次
    -0.06
    raries
    -0.06
    åŀ£
    -0.06
    ENZ
    -0.06
    æŃ¤æ¥¼
    -0.06
    vez
    -0.06
    WithTag
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    isu
    0.07
    å¿ĺåį´
    0.07
    ç»ĻæĪij们带æĿ¥
    0.07
    etes
    0.07
    çļĦ主ä½ĵ
    0.07
    話說
    0.07
    esti
    0.06
    äºİä¸ĸ
    0.06
    ÙĬØŃ
    0.06
    Activations Density 0.293%

    No Known Activations