© 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. 62213
    Prev
    Next
    INDEX
    Explanations

    ratio / denominator

    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
    .Lib
    -0.10
    иÑĢо
    -0.10
    继ç»Ńéĺħ读
    -0.08
    æľ¬ç½ij
    -0.08
    书åŁİ
    -0.08
     respeit
    -0.08
    åIJĮæ¯Ķåĩıå°ij
    -0.08
    微信æī«çłģ
    -0.08
    è°ģ家
    -0.08
    æĥ³ä½ł
    -0.08
    POSITIVE LOGITS
     cad
    0.07
    åįłæĢ»
    0.07
     Cad
    0.07
    anic
    0.07
    /(
    0.06
     ratio
    0.06
     denominator
    0.06
     /(
    0.06
     Gam
    0.06
     Indo
    0.06
    Activations Density 0.044%

    No Known Activations