© 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. 39855
    Prev
    Next
    INDEX
    Explanations

    system and data descriptions

    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
    aggi
    -0.08
    anita
    -0.07
    åİī害
    -0.07
    åĭĴ
    -0.07
    Placeholder
    -0.07
    åľ¨èĩªå·±
    -0.07
    /count
    -0.07
     Agricultura
    -0.07
    fad
    -0.07
     liá»ĩt
    -0.07
    POSITIVE LOGITS
    pher
    0.08
     timing
    0.08
     overall
    0.08
    æķ´ä½ĵ
    0.08
    çļĦæķ´ä½ĵ
    0.08
    iddleware
    0.07
     Overall
    0.07
    管çIJĨçŃī
    0.07
    timing
    0.07
    æķ´ä½ĵçļĦ
    0.07
    Activations Density 0.378%

    No Known Activations