© 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. 24316
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming

    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
    oldt
    -0.07
     ful
    -0.07
    odes
    -0.06
    æ··
    -0.06
    岸
    -0.06
    icle
    -0.06
    æ©
    -0.06
    ilog
    -0.06
    ippo
    -0.06
    çĥĺçĦĻ
    -0.06
    POSITIVE LOGITS
    çļĦæ°ĶåĬ¿
    0.08
    agin
    0.08
    交æµģä¸İåIJĪä½ľ
    0.07
    è¯¥ä½ľèĢħ
    0.07
    ÙħÙĪد
    0.07
    åĪ¹éĤ£éĹ´
    0.07
    æľīç¦ı
    0.07
    æľī责任å¿ĥ
    0.07
    versa
    0.07
     Porta
    0.07
    Activations Density 0.001%

    No Known Activations