© 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. 1056
    Prev
    Next
    INDEX
    Explanations

    baking ingredients and cooking terms

    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
     locally
    -0.06
    å®Ĺ
    -0.06
     reconstructed
    -0.06
    arik
    -0.06
     Chain
    -0.06
    精巧
    -0.06
     formally
    -0.06
     âĢŀ
    -0.06
     Sector
    -0.05
    yclic
    -0.05
    POSITIVE LOGITS
    æĬ¥è®¯
    0.10
    ä¸ŃéĢĶ
    0.10
    [âĢ¦
    0.10
     Reinh
    0.09
    ssp
    0.09
    éĵģé¾Ļ
    0.09
    æ¡ĤåĨł
    0.09
    çļĦå°ıä¼Ļä¼´
    0.09
     Famili
    0.09
    placeholders
    0.09
    Activations Density 0.131%

    No Known Activations