© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46798
    Prev
    Next
    INDEX
    Explanations

    in this case,

    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
    é¦ĸåħĪåľ¨
    -0.08
    elay
    -0.07
    æľ¬èº«çļĦ
    -0.07
    æľŁæ»¡åIJİ
    -0.07
    acker
    -0.07
    |-
    -0.07
    åĩıå°ij对
    -0.07
    å¸¸åľ¨
    -0.07
    áīµ
    -0.07
    常æľī
    -0.07
    POSITIVE LOGITS
     particular
    0.07
    zul
    0.07
    ä¹Ŀå¹´
    0.07
     ÑģлÑĥÑĩаÑı
    0.07
     context
    0.07
    ä¸ī个åŃĹ
    0.06
    ä¹Łä¸įä¾ĭå¤ĸ
    0.06
    ämt
    0.06
    ÑĢане
    0.06
     case
    0.06
    Activations Density 0.112%

    No Known Activations