© 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. 34817
    Prev
    Next
    INDEX
    Explanations

    steps, scenario, or notes followed by a colon

    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
    ecure
    -0.08
    \'\
    -0.07
     nhau
    -0.07
    ä¸ĭèį¯
    -0.07
    æ¯ķç«Ł
    -0.07
    ä¹ħä¹ĭ
    -0.07
    ciu
    -0.07
    ycz
    -0.07
    orgia
    -0.07
     #@
    -0.07
    POSITIVE LOGITS
    oz
    0.07
    åĤĻ
    0.07
    noon
    0.06
    Unnamed
    0.06
    -setting
    0.06
     Verde
    0.06
    astas
    0.06
    tian
    0.06
     Setup
    0.06
    ľ
    0.06
    Activations Density 0.001%

    No Known Activations