© 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. 12452
    Prev
    Next
    INDEX
    Explanations

    `trueč`

    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
    ibi
    -0.06
    رÙĬت
    -0.06
    æĺİæĹ¥
    -0.06
    à¸Ĺม
    -0.06
    zm
    -0.06
    tracts
    -0.06
    ä¸Ĭ级é¢Ĩ导
    -0.06
    æļĹå¤ľ
    -0.06
    ç»ĪæĹ¥
    -0.06
    .prompt
    -0.06
    POSITIVE LOGITS
    atlan
    0.08
    versions
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    ernels
    0.07
    ä¸ĢåĽ¾
    0.07
     ÐłÐµÐ·Ñĥ
    0.07
     Kem
    0.07
     αÏĢαÏģα
    0.07
     fác
    0.07
    tees
    0.07
    Activations Density 0.041%

    No Known Activations