© 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. 28250
    Prev
    Next
    INDEX
    Explanations

    randomness and luck

    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
     леп
    -0.07
    رÙĬج
    -0.07
    abl
    -0.07
    æī¬
    -0.07
    logg
    -0.07
    çĤľ
    -0.07
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.07
     "`
    -0.07
    ç»´æĸ¯
    -0.06
    /=
    -0.06
    POSITIVE LOGITS
     randomly
    0.18
    éļıæľº
    0.17
     random
    0.16
    幸è¿IJ
    0.16
    è¿IJæ°Ķ
    0.15
    random
    0.15
     randomness
    0.15
     Random
    0.14
    åģ¶çĦ¶
    0.14
     luck
    0.14
    Activations Density 0.299%

    No Known Activations