© 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. 22247
    Prev
    Next
    INDEX
    Explanations

    split, grep, regex, decode

    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
    ier
    -0.08
    çĻ¾è®¡
    -0.08
    ONUS
    -0.08
    æĿ¡ä»¶æĺ¯
    -0.07
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.07
    ONENT
    -0.07
    踢
    -0.07
     khả
    -0.07
    ×Ļ×ķת
    -0.07
    æľµèĬ±
    -0.07
    POSITIVE LOGITS
    åĬĽæĮº
    0.06
    CADE
    0.06
    éĩĮäºļ
    0.06
    ẩm
    0.06
    ujung
    0.06
    èĽĬ
    0.06
    æıIJ
    0.06
    .bits
    0.06
    .lines
    0.06
     Turbo
    0.06
    Activations Density 0.006%

    No Known Activations