© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    english language publications

    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
    getDefault
    -0.08
    è®¤çľŁåģļ好
    -0.07
    åģļä¸įåĪ°
    -0.07
    igenza
    -0.07
    icoli
    -0.07
    ariat
    -0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    -0.07
    æĢĿæºIJ
    -0.07
    人åIJį
    -0.07
    zte
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.09
    ãģĭãģ¤
    0.08
     isValid
    0.08
     candidates
    0.08
    符åIJĪè¦ģæ±Ĥ
    0.08
     fits
    0.08
    åĮ¹éħį
    0.08
    ä¸Ķä¸į
    0.08
    Candidate
    0.08
    _candidates
    0.08
    Activations Density 0.011%

    No Known Activations