© 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. 65492
    Prev
    Next
    INDEX
    Explanations

    probability, likelihood, cover time, extinction, chains, determine, claim

    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
    ä¸įè°ĥ
    -0.08
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    -0.08
    RI
    -0.06
    ä¸įå¾Ĺ以任ä½ķ
    -0.06
     pul
    -0.06
    ä¾Ŀæ³ķèĩªä¸»
    -0.06
    CALE
    -0.06
    erra
    -0.06
     Insp
    -0.06
    IDER
    -0.06
    POSITIVE LOGITS
     Probability
    0.09
     probabilities
    0.09
     probability
    0.09
    Probability
    0.09
    æ¦Ĥçİĩ
    0.08
    walker
    0.08
     walkers
    0.08
    èµĮåįļ
    0.08
    probability
    0.08
     infinite
    0.08
    Activations Density 0.008%

    No Known Activations