© 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. 41874
    Prev
    Next
    INDEX
    Explanations

    demonstrating proof

    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
    æĢĿ
    -0.07
    olong
    -0.06
    ìį¨
    -0.06
     ister
    -0.06
     unto
    -0.06
    åĽĽçº§
    -0.06
    å¯Ĥ
    -0.06
    ibas
    -0.06
    ayed
    -0.06
    iens
    -0.06
    POSITIVE LOGITS
    ç¡®å®ŀæĺ¯
    0.09
    çļĦç¡®
    0.08
    æ¦Ľ
    0.08
    uffman
    0.08
    éĺ´æ²ī
    0.07
     NDEBUG
    0.07
     Bogor
    0.07
    γκα
    0.07
    sov
    0.07
    é»Ħæ²Ļ
    0.07
    Activations Density 0.074%

    No Known Activations