© 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. 45603
    Prev
    Next
    INDEX
    Explanations

    well, highly, just, item, Southern

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
     b
    -0.07
    ixon
    -0.06
    åİĭ榨
    -0.06
    åıĸåĨ³
    -0.06
     bist
    -0.06
    oby
    -0.06
     Downing
    -0.06
     de
    -0.06
    åİĭ
    -0.06
    POSITIVE LOGITS
    æĥ£
    0.09
    ×ij׾
    0.08
    åħ¢
    0.08
    æľ¬ç«ĻæīĢæľī
    0.08
    èĭ±æīį
    0.08
    chst
    0.08
    keit
    0.08
    ç²Ľ
    0.08
    emel
    0.08
    ç«łèĬĤ缮å½ķ
    0.08
    Activations Density 0.167%

    No Known Activations