© 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. 39009
    Prev
    Next
    INDEX
    Explanations

    finding derivatives

    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
    pha
    -0.09
    isah
    -0.09
    éh
    -0.08
    phan
    -0.08
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    -0.08
    út
    -0.08
    çīĪåĽ¾
    -0.08
    Ñijма
    -0.08
     ={
    -0.07
    æĽĻ
    -0.07
    POSITIVE LOGITS
    åĬłéĢŁ
    0.08
    稳å®ļ
    0.07
    éħ·
    0.07
     constant
    0.06
    raw
    0.06
    eler
    0.06
    ä¸įç»Ŀ
    0.06
    æģĴå®ļ
    0.06
     quadr
    0.06
    accel
    0.06
    Activations Density 0.004%

    No Known Activations