© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19194
    Prev
    Next
    INDEX
    Explanations

    drive or cylinder

    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
    Not in Any Lists

    No Comments

    Negative Logits
    vell
    -0.08
    海绵
    -0.08
    iels
    -0.07
    meer
    -0.07
    é«ĺæł¡çĶŁ
    -0.07
    æķ
    -0.07
    åįıåIJĮ
    -0.07
    pong
    -0.07
    asser
    -0.07
    stell
    -0.07
    POSITIVE LOGITS
    tar
    0.08
    spiracy
    0.07
     either
    0.07
     particular
    0.07
    ×Ļ׾×ķת
    0.06
     whenever
    0.06
    zer
    0.06
     pict
    0.06
     –
    0.06
    Ñĥл
    0.06
    Activations Density 0.001%

    No Known Activations