© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    non-

    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
     instead
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    代ãĤıãĤĬãģ«
    -0.08
    说å¾Ĺ
    -0.08
    ä¸įæ¯Ķ
    -0.07
    ä¸įçĶļ
    -0.07
     μην
    -0.07
    ä¸įæĺ¯å¾Ī
    -0.07
    ä¸įçŁ¥éģĵ该
    -0.07
    instead
    -0.07
    POSITIVE LOGITS
     anymore
    0.10
     sondern
    0.09
     necessarily
    0.08
    å°Ħ
    0.08
     nor
    0.08
    èĢĮæĺ¯
    0.08
    ç«ĭåį³
    0.08
     sino
    0.07
    uros
    0.07
     hanem
    0.07
    Activations Density 0.142%

    No Known Activations