© 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. 32544
    Prev
    Next
    INDEX
    Explanations

    factorial calculations

    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
    -ajax
    -0.09
    witch
    -0.09
    åį«ä¸ľ
    -0.08
    äºĮä½į
    -0.08
    夫妻俩
    -0.08
    ijo
    -0.07
    átk
    -0.07
    举èĬĿ
    -0.07
    秧
    -0.07
    ellij
    -0.07
    POSITIVE LOGITS
     factorial
    0.09
     vig
    0.07
    .factor
    0.07
    éĩĬ
    0.07
    oen
    0.07
    åĽłåŃIJ
    0.07
     ruk
    0.06
    atu
    0.06
     abbr
    0.06
    dex
    0.06
    Activations Density 0.011%

    No Known Activations