© 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. 57399
    Prev
    Next
    INDEX
    Explanations

    homogeneous coordinates, mixture design

    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
    Rent
    -0.07
    rote
    -0.07
    ork
    -0.07
    iphy
    -0.07
    éĢįéģ¥
    -0.07
    åĽŃåľ°
    -0.07
    (dm
    -0.07
    eck
    -0.06
    oare
    -0.06
    Ĵ
    -0.06
    POSITIVE LOGITS
     tá»ī
    0.08
    ailles
    0.08
    æ¯Ķä¾ĭ
    0.08
     proportions
    0.07
    æĬķ
    0.07
    ä»Ĺ
    0.07
     ratios
    0.07
    éħįæ¯Ķ
    0.07
    æ¯Ķä¾ĭ为
    0.07
    acara
    0.07
    Activations Density 0.001%

    No Known Activations