© 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. 40641
    Prev
    Next
    INDEX
    Explanations

    piecewise functions and relations

    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
    egi
    -0.07
    缴æİ¥æĪĸ
    -0.07
    werks
    -0.07
    less
    -0.07
    åĽ¢æĪIJåijĺ
    -0.07
     Structural
    -0.06
    æĽ´åģ¥åº·
    -0.06
    bole
    -0.06
    æ®·åĪĩ
    -0.06
    pare
    -0.06
    POSITIVE LOGITS
    edal
    0.08
    alik
    0.07
    çĻ½è¡Ģ
    0.07
    _FOREACH
    0.07
    etting
    0.07
    æĹ¥çĶµ
    0.07
    ayout
    0.06
    /manage
    0.06
    å£Ĭ
    0.06
    appa
    0.06
    Activations Density 0.006%

    No Known Activations