© 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. 31786
    Prev
    Next
    INDEX
    Explanations

    spherical symmetry

    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
    æݧ
    -0.08
    иÑĤоÑĢ
    -0.08
    tori
    -0.08
    .ly
    -0.08
    waan
    -0.07
    è¿ŀçݯ
    -0.07
    emoth
    -0.07
     Letras
    -0.07
     separat
    -0.07
    æķħäºĭæĥħ
    -0.07
    POSITIVE LOGITS
    çIJĥå½¢
    0.09
    åĿĩåĮĢ
    0.09
    åĿĩåĮĢçļĦ
    0.09
     uniform
    0.08
     isot
    0.08
     randomness
    0.08
    uniform
    0.08
    /random
    0.08
    avs
    0.07
    _uniform
    0.07
    Activations Density 0.004%

    No Known Activations