© 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. 719
    Prev
    Next
    INDEX
    Explanations

    func, fn, or code identifiers

    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
    æī§çºª
    -0.07
    andid
    -0.07
    è§Ĥæij©
    -0.07
    =#
    -0.06
    寿åı¸
    -0.06
    ibbon
    -0.06
    reen
    -0.06
    ichel
    -0.06
    åħ³
    -0.06
    .model
    -0.06
    POSITIVE LOGITS
    åĥ¹
    0.07
    neos
    0.07
    BufferData
    0.07
    поло
    0.07
    اÙĨس
    0.07
    zan
    0.07
    æ³°
    0.07
    GAN
    0.07
    zzi
    0.06
    PWD
    0.06
    Activations Density 0.063%

    No Known Activations