© 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. 43020
    Prev
    Next
    INDEX
    Explanations

    superconductivity, electricity, alcoholic, malignancy

    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
    ingan
    -0.09
    otec
    -0.08
    seys
    -0.08
    باÙĨ
    -0.08
    sdale
    -0.08
    Öģ
    -0.08
    rš
    -0.08
    -match
    -0.08
    alba
    -0.07
     {?}
    -0.07
    POSITIVE LOGITS
    æĦıæĥ³ä¸įåĪ°çļĦ
    0.08
    -like
    0.07
     via
    0.07
     emerge
    0.07
    æĦıå¤ĸçļĦ
    0.06
     emerged
    0.06
     emerges
    0.06
    idio
    0.06
     underneath
    0.06
    via
    0.06
    Activations Density 0.124%

    No Known Activations