© 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. 22295
    Prev
    Next
    INDEX
    Explanations

    stable isotopes

    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
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.09
    ä¸įåĪ°çļĦ
    -0.08
     nhau
    -0.08
    ÑģÑĤва
    -0.08
    ers
    -0.08
    naire
    -0.07
    à¹Ħร
    -0.07
    注æĦıäºĨ
    -0.07
    shan
    -0.07
    ual
    -0.07
    POSITIVE LOGITS
    -looking
    0.10
    er
    0.09
    -ish
    0.09
    ëį°
    0.09
    oftware
    0.08
    ÑģÑĮ
    0.08
    psilon
    0.08
    à®ķ
    0.08
    OperationException
    0.08
    evice
    0.08
    Activations Density 0.031%

    No Known Activations