© 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. 32649
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    sein
    -0.08
    _RPC
    -0.07
    rne
    -0.07
    rary
    -0.07
     wherever
    -0.06
    двига
    -0.06
    cock
    -0.06
     mont
    -0.06
    blog
    -0.06
    à¸Ħร
    -0.06
    POSITIVE LOGITS
    Å¡Å¥
    0.08
    ires
    0.07
    aras
    0.07
    ieras
    0.07
    翼翼
    0.07
    çĶļèĩ³æľīäºĽ
    0.07
    ijĺ
    0.07
    ombs
    0.07
    ળ
    0.07
    ora
    0.07
    Activations Density 0.039%

    No Known Activations