© 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. 23163
    Prev
    Next
    INDEX
    Explanations

    ellipse, ellipsoid, elliptical

    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
    é¾Ħ
    -0.07
    è¡Ķ
    -0.07
    resa
    -0.07
    大æłij
    -0.07
    åIJIJ
    -0.07
    åĩ
    -0.07
    /module
    -0.07
    VOKE
    -0.07
    æ¶Į
    -0.07
     trÃł
    -0.07
    POSITIVE LOGITS
    æ¤Ń
    0.09
     axes
    0.09
     ellipt
    0.09
    Stretch
    0.09
    æĭī伸
    0.09
    unia
    0.09
     stretching
    0.08
     ellipse
    0.08
     distort
    0.08
     ell
    0.08
    Activations Density 0.018%

    No Known Activations