© 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. 29443
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
     Factors
    -0.07
    écr
    -0.07
    ospace
    -0.07
    .functional
    -0.07
    ieb
    -0.07
     messing
    -0.07
     factors
    -0.07
    æĹłéļľç¢į
    -0.07
    -worthy
    -0.07
    !!!!!!!!
    -0.07
    POSITIVE LOGITS
     пÑĢинÑĨипÑĥ
    0.13
    åİŁçIJĨ
    0.12
    çļĦåİŁçIJĨ
    0.12
    æĢĿè·¯
    0.12
     principle
    0.12
    åŁºæľ¬åİŁçIJĨ
    0.12
    çļĦæĢĿè·¯
    0.11
    æĺ¯åĪ©çĶ¨
    0.11
    çļĦå·¥ä½ľåİŁçIJĨ
    0.11
     ÐŁÑĢинÑĨип
    0.11
    Activations Density 0.363%

    No Known Activations