© 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. 1409
    Prev
    Next
    INDEX
    Explanations

    class amplifier or correct

    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
    åŃ½
    -0.06
    åĤĺ
    -0.06
    åįĬ个
    -0.06
    اÙĨØ©
    -0.06
    enia
    -0.06
    æķĽ
    -0.06
    åł
    -0.06
    gli
    -0.06
    indre
    -0.06
     baz
    -0.05
    POSITIVE LOGITS
    代ä¼ļ
    0.08
    çīĪæĿĥæīĢæľī
    0.08
    æĹłæĢ¨
    0.08
    ãĤ·ãĥ£ãĥ¼
    0.08
    ÑİÑĢ
    0.08
    oller
    0.08
    جر
    0.08
    ieux
    0.08
    åłªèĥ½
    0.08
    riet
    0.07
    Activations Density 0.006%

    No Known Activations