© 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. 4341
    Prev
    Next
    INDEX
    Explanations

    given

    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
    ilus
    -0.08
    gn
    -0.07
    æĢİä¹ĪéĢī
    -0.07
    STS
    -0.07
    GN
    -0.07
    	Response
    -0.07
    foundland
    -0.06
     clearTimeout
    -0.06
     Brend
    -0.06
    éĺ¿æĭī伯
    -0.06
    POSITIVE LOGITS
    ymm
    0.08
     given
    0.08
    ç»Ļå®ļ
    0.07
    è°ĭ
    0.07
    нала
    0.07
     represented
    0.07
    given
    0.07
     indicated
    0.07
     IMPLIED
    0.07
    Vec
    0.07
    Activations Density 0.232%

    No Known Activations