© 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. 55977
    Prev
    Next
    INDEX
    Explanations

    guessing or uncertainty

    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
    trag
    -0.09
    æĪijåij¢
    -0.08
    æľ¬èº«å°±
    -0.08
    ä»ĸèĩªå·±
    -0.08
    æĪij个人
    -0.08
    æĪijåį´
    -0.08
     itself
    -0.07
    Õ§
    -0.07
     themselves
    -0.07
     formally
    -0.07
    POSITIVE LOGITS
     probable
    0.10
     likely
    0.09
    æݨæĸŃ
    0.08
    _UNUSED
    0.08
    ough
    0.08
    യാ
    0.07
    usalem
    0.07
     Likely
    0.07
    likely
    0.07
    اب
    0.07
    Activations Density 0.011%

    No Known Activations