© 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. 49138
    Prev
    Next
    INDEX
    Explanations

    cannot know what to

    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
    åļ´
    -0.07
    hati
    -0.07
    Memo
    -0.07
    odox
    -0.07
    è¿ĺåºĶ该
    -0.07
    _should
    -0.07
     accept
    -0.07
    laub
    -0.06
    æĬĬè¿Ļ
    -0.06
    expo
    -0.06
    POSITIVE LOGITS
    çļĦåīįæıIJ
    0.14
    æĹłä»İ
    0.13
     presup
    0.13
    åīįæıIJ
    0.12
    éľĢè¦ģæľī
    0.10
    åĩŃ空
    0.10
    åīįæıIJæĺ¯
    0.10
    åĽłä¸ºæ²¡æľī
    0.09
    gar
    0.09
    çļĦåŁºç¡Ģ
    0.09
    Activations Density 0.191%

    No Known Activations