© 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. 38296
    Prev
    Next
    INDEX
    Explanations

    apply heat or force

    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
     reass
    -0.07
    弥补
    -0.07
    åĮĸ为
    -0.07
    èĢ½
    -0.07
    åĮĸæĪIJ
    -0.06
    åľ¨ä»ĬåIJİ
    -0.06
    æ³ķå¾ĭ顾éĹ®
    -0.06
    orage
    -0.06
    writes
    -0.06
    comed
    -0.06
    POSITIVE LOGITS
    使ä¹ĭ
    0.12
    使åħ¶
    0.10
    使å®ĥ
    0.09
     slowly
    0.09
    å°ıå¿ĥ
    0.09
    åı¯ä»¥ä½¿
    0.08
     deliberately
    0.08
    使
    0.08
    让åħ¶
    0.08
    让è¿Ļ个
    0.08
    Activations Density 0.180%

    No Known Activations