© 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. 51605
    Prev
    Next
    INDEX
    Explanations

    genes and alleles

    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
    è¾ĵ
    -0.07
    çĢļ
    -0.06
    ä¹ĭ缮çļĦ
    -0.06
    æĺ¯èĩªå·±
    -0.06
    æ´ŀ
    -0.06
    ette
    -0.05
    æĿī
    -0.05
    æ³
    -0.05
     minib
    -0.05
    ä¸īéĥ¨
    -0.05
    POSITIVE LOGITS
    orter
    0.08
     bersifat
    0.08
    abbit
    0.08
    беÑĢе
    0.08
    以太
    0.08
    _traits
    0.08
    .codes
    0.07
     nutris
    0.07
    aes
    0.07
     gén
    0.07
    Activations Density 0.012%

    No Known Activations