© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37562
    Prev
    Next
    INDEX
    Explanations

    compact sets and convergence

    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
    Negative Logits
    olak
    -0.09
    .newBuilder
    -0.08
    @qq
    -0.08
    auff
    -0.07
    .Quad
    -0.07
    æľīäºĽäºĭ
    -0.07
    egrity
    -0.07
    -drop
    -0.07
    amento
    -0.06
    анием
    -0.06
    POSITIVE LOGITS
    -away
    0.07
    away
    0.07
    æľĪä¸Ń
    0.07
    è¿ľç¦»
    0.07
    AHA
    0.07
    ä¸Ĭ使çĶ¨
    0.07
    ListOf
    0.07
    ombat
    0.07
    Toast
    0.07
    oller
    0.07
    Activations Density 0.003%

    No Known Activations