© 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. 8859
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    绢
    -0.07
    åľ¨å¤©
    -0.06
    Shader
    -0.06
    ic
    -0.06
     *(*
    -0.06
    erden
    -0.06
    åĹĵåŃIJ
    -0.06
    åĵ²
    -0.06
    åľ¨ç©ºä¸Ń
    -0.06
    jk
    -0.06
    POSITIVE LOGITS
    trup
    0.10
    è±Ĩè±Ĩ
    0.09
    æĪijä¹Łä¸įçŁ¥éģĵ
    0.07
    .documentation
    0.07
    Verifier
    0.07
    请äºİ
    0.07
    reja
    0.07
    EMAT
    0.06
    _ZONE
    0.06
    _RM
    0.06
    Activations Density 0.844%

    No Known Activations