© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16041
    Prev
    Next
    INDEX
    Explanations

    homozygous

    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
    æł¼æĭīæĸ¯
    -0.09
    illard
    -0.09
    ianos
    -0.09
    麾
    -0.08
    лле
    -0.08
    iveness
    -0.08
    ä¸Ńçݯ
    -0.08
    ÛĮات
    -0.08
    æľªå°½
    -0.08
    geving
    -0.08
    POSITIVE LOGITS
     recess
    0.06
    ity
    0.06
    azed
    0.06
    çļĦç»ĵæŀľ
    0.06
    utz
    0.06
    éĹĨ
    0.06
    æ·±èī²
    0.06
    afa
    0.06
    orsk
    0.06
    ITY
    0.06
    Activations Density 0.005%

    No Known Activations