© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    everything else

    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
    ugio
    -0.08
    à¸ģระà¸Ĺ
    -0.08
    åĢ©
    -0.08
    ׼×Ŀ
    -0.08
    ================================================================
    -0.08
     utterly
    -0.07
    å®Įåħ¨æ²¡æľī
    -0.07
    å®Įåħ¨ä¸į
    -0.07
    mitt
    -0.07
     fullPath
    -0.07
    POSITIVE LOGITS
     else
    0.11
     تÙĤرÙĬب
    0.10
     around
    0.09
    else
    0.08
    around
    0.08
    elos
    0.07
    THING
    0.07
    iin
    0.07
    	else
    0.07
    ernes
    0.07
    Activations Density 0.065%

    No Known Activations