© 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. 18886
    Prev
    Next
    INDEX
    Explanations

    grinding mill

    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
    ê¹IJ
    -0.11
    waard
    -0.09
    ลฯ
    -0.09
    rane
    -0.09
    tdown
    -0.09
    ä¸Ģæĸij
    -0.09
    ãĥIJãĥ³ãĤ¯
    -0.09
    incinn
    -0.09
    ï¸ı
    -0.09
    bish
    -0.09
    POSITIVE LOGITS
    çĽ¹
    0.08
    out
    0.07
    äºĨä¸Ģ
    0.07
    ings
    0.07
    0.07
    lot
    0.07
    ynet
    0.06
    èµ·äºĨ
    0.06
    ówczas
    0.06
     Pesso
    0.06
    Activations Density 0.004%

    No Known Activations