© 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. 1200
    Prev
    Next
    INDEX
    Explanations

    reciprocal temporary

    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
    ëĦ¤
    -0.07
    uster
    -0.07
    ç¼ī
    -0.07
    ä¸įçĶĺ
    -0.06
    æģ©æĸ¯
    -0.06
    ÙĪرÙĬØ©
    -0.06
    æ¯ĶåĪ©
    -0.06
     bog
    -0.06
    íķij
    -0.06
    éĢļè¿ĩè¿Ļ次
    -0.06
    POSITIVE LOGITS
     esclus
    0.09
    ertest
    0.08
    æļ¦
    0.08
    integration
    0.08
    abela
    0.08
    øv
    0.08
    æ²¹
    0.08
    [char
    0.08
    è½®æµģ
    0.07
    ä¸įåıij
    0.07
    Activations Density 0.012%

    No Known Activations