© 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. 38287
    Prev
    Next
    INDEX
    Explanations

    extract coefficients, ratios

    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
    _ie
    -0.07
     vaj
    -0.06
     predetermined
    -0.06
    DT
    -0.06
    åĪĴ
    -0.06
    身
    -0.05
    æ¹ĺæ±Ł
    -0.05
    æĹ¢æĺ¯
    -0.05
    OB
    -0.05
     DT
    -0.05
    POSITIVE LOGITS
    è´¡çĮ®
    0.09
    ratio
    0.09
    æ¯Ķä¾ĭ
    0.09
     ratios
    0.09
    æ¯Ķä¾ĭ为
    0.08
    _proxy
    0.08
     Contributions
    0.08
    çĻŀ
    0.08
    åı¯è°ĥ
    0.08
    åĽ¾è°±
    0.08
    Activations Density 0.003%

    No Known Activations