© 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. 34956
    Prev
    Next
    INDEX
    Explanations

    code markdown or linux headers

    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
    åĩł
    -0.07
    ieger
    -0.07
    .har
    -0.06
    åĩłçĻ¾
    -0.06
    اد
    -0.06
     Harding
    -0.06
    æijĩäºĨ
    -0.06
    mvc
    -0.06
    èĭ¥åľ¨
    -0.05
    -striped
    -0.05
    POSITIVE LOGITS
    glas
    0.09
    ABCDEFG
    0.09
    alis
    0.08
    ARTH
    0.07
    _tA
    0.07
    cx
    0.07
    æ²³çķĶ
    0.07
    %E
    0.07
    ç£ĭ
    0.07
    arzy
    0.07
    Activations Density 0.001%

    No Known Activations