© 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. 46122
    Prev
    Next
    INDEX
    Explanations

    suggests or indicates variation

    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
    æį®ä»ĭç»į
    -0.08
     schlieÃŁlich
    -0.08
    被èªī为
    -0.07
    OTE
    -0.07
    åĽłä¸ºæ²¡æľī
    -0.07
    说è¦ģ
    -0.07
    neos
    -0.07
    çłĶ究表æĺİ
    -0.07
    egov
    -0.07
    为åķ¥
    -0.07
    POSITIVE LOGITS
     somehow
    0.16
    æŁIJç§į
    0.12
     somewhere
    0.12
     something
    0.10
    èĩ³å°ijåľ¨
    0.09
     indeed
    0.09
    æľīå¤ļä¹Ī
    0.09
     Something
    0.08
    æŁIJ種
    0.08
     ê·¸ë§Įíģ¼
    0.08
    Activations Density 0.114%

    No Known Activations