© 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. 26394
    Prev
    Next
    INDEX
    Explanations

    intensity scale

    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
    à§ĭধ
    -0.09
    éģĹçĹĩ
    -0.08
     infinity
    -0.08
    heim
    -0.08
    POOL
    -0.08
    éĤ£ä¹Īç®Ģåįķ
    -0.08
     makin
    -0.08
    æĹłéĻIJ
    -0.07
    ÙĪÙĬب
    -0.07
    deen
    -0.07
    POSITIVE LOGITS
     sekali
    0.12
     enough
    0.10
     (>
    0.10
    (er
    0.09
     genug
    0.08
    ests
    0.08
    stens
    0.08
     ×ŀ×IJ×ķ×ĵ
    0.08
    ely
    0.07
    ÃŃsima
    0.07
    Activations Density 0.299%

    No Known Activations