© 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. 13868
    Prev
    Next
    INDEX
    Explanations

    Donaldson Converge cookies eyes community Block Respond

    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
    TEL
    -0.09
    .mdl
    -0.08
    butt
    -0.08
    ä¸ĩ平米
    -0.07
    ough
    -0.07
    ÙĪÙĨس
    -0.07
    ளà¯į
    -0.07
    enville
    -0.07
    ä¸ĩåį·
    -0.07
    é«ĺ人
    -0.07
    POSITIVE LOGITS
    uge
    0.07
    geb
    0.07
    ichen
    0.07
    ju
    0.07
    碧
    0.07
    è§ģæĪij
    0.06
    cales
    0.06
    Äįek
    0.06
    loh
    0.06
    åī§åľº
    0.06
    Activations Density 1.140%

    No Known Activations