© 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. 37443
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    apore
    -0.08
    ÑģÑĤок
    -0.08
    azer
    -0.07
    ¯
    -0.07
    opor
    -0.07
     filmy
    -0.07
    _UNIFORM
    -0.07
    _SELECTION
    -0.07
     unwrap
    -0.07
    ë¦Ħ
    -0.07
    POSITIVE LOGITS
    åĩij
    0.08
     evaluating
    0.08
    eval
    0.07
    insk
    0.07
    Plug
    0.07
     evaluates
    0.07
     Evalu
    0.07
    代åħ¥
    0.07
    renderer
    0.07
     evaluate
    0.07
    Activations Density 0.020%

    No Known Activations