© 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. 10034
    Prev
    Next
    INDEX
    Explanations

    selection and choosing

    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
    éĺħè¯»æľ¬æĸĩ
    -0.08
    -friendly
    -0.07
    riendly
    -0.07
    åıĭ好çļĦ
    -0.07
    ç±»åŀĭ为
    -0.07
    第ä¸ĥç«ł
    -0.07
    idy
    -0.07
    è½¼
    -0.07
    åĹĸ
    -0.07
    inea
    -0.07
    POSITIVE LOGITS
    åIJįåįķ
    0.11
     list
    0.10
     lists
    0.10
     Lists
    0.10
     ìĦłìłķ
    0.09
     selections
    0.09
     List
    0.09
     selection
    0.09
    ãĥªãĤ¹ãĥĪ
    0.09
     Selection
    0.09
    Activations Density 0.072%

    No Known Activations