© 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. 58203
    Prev
    Next
    INDEX
    Explanations

    run with checkboxes

    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
    uva
    -0.07
    æĻķ
    -0.07
    auss
    -0.06
    ä¸Ģåĩ»
    -0.06
    YLE
    -0.06
    еÑĢÑĤ
    -0.06
    çIJĨåĮĸ
    -0.06
    åħ¬æīĢ
    -0.06
    nof
    -0.06
    ZER
    -0.06
    POSITIVE LOGITS
    olib
    0.07
    olis
    0.07
    éĥ½åIJĪ
    0.07
    åıĮ人
    0.07
    _hdl
    0.07
    æĻ®éĢļçļĦ
    0.07
     bern
    0.06
    ansen
    0.06
    æĹ¢çĦ¶æĺ¯
    0.06
     super
    0.06
    Activations Density 0.254%

    No Known Activations