© 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. 19474
    Prev
    Next
    INDEX
    Explanations

    different formatting differences

    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
    lesa
    -0.08
     ThemeData
    -0.08
    bacher
    -0.07
    Õ°
    -0.07
    oble
    -0.07
    коми
    -0.07
    ç§Ģ丽
    -0.07
    odem
    -0.07
    éĢĨæµģ
    -0.07
    TEGR
    -0.07
    POSITIVE LOGITS
     ambiguous
    0.11
    ambiguous
    0.10
     ambiguity
    0.10
    æĦıåĽ¾
    0.09
     default
    0.08
    é»ĺ认
    0.08
    约å®ļ
    0.08
     Amb
    0.08
    asal
    0.08
    ä¸įæĺİç¡®
    0.08
    Activations Density 0.016%

    No Known Activations