© 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. 8513
    Prev
    Next
    INDEX
    Explanations

    court, appeals, texas

    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
    Ø©
    -0.12
    c
    -0.08
    s
    -0.08
    o
    -0.08
    i
    -0.08
    aka
    -0.07
    ka
    -0.07
    ness
    -0.07
    âĢ¦
    -0.07
    t
    -0.07
    POSITIVE LOGITS
    èĩªå·±æ²¡æľī
    0.13
    èĩªå·±
    0.12
    raries
    0.11
    èĩªå·±è¢«
    0.11
    éģĹçĹĩ
    0.10
    estroy
    0.10
    èĩªå·±èº«ä¸Ĭ
    0.10
    à§įস
    0.09
    enam
    0.09
    erness
    0.09
    Activations Density 0.180%

    No Known Activations