© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    non-english unicode characters

    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
     Wür
    -0.08
    áĥŃ
    -0.08
    ilian
    -0.08
    iante
    -0.08
    Wür
    -0.07
    _FINE
    -0.07
    verso
    -0.07
    prü
    -0.07
     **.**
    -0.07
    uesa
    -0.07
    POSITIVE LOGITS
    icka
    0.07
    ап
    0.07
    æł
    0.07
     sov
    0.06
    éĽĨ
    0.06
    lair
    0.06
    à¹Ģà¸Ħ
    0.06
    asia
    0.06
    æĬ±
    0.06
    æ¦Ħ
    0.06
    Activations Density 0.146%

    No Known Activations