© 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. 50755
    Prev
    Next
    INDEX
    Explanations

    derived from plants and animals

    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
    -comm
    -0.08
    ãĥĿãĥªãĤ¨ãĤ¹ãĥĨ
    -0.08
    æŀľåĵģ
    -0.07
    檸
    -0.07
    èĶ¬
    -0.07
    ?id
    -0.07
     topLevel
    -0.07
    renz
    -0.07
    èĨĬ
    -0.07
    ↵				↵
    -0.07
    POSITIVE LOGITS
    -derived
    0.14
     extracts
    0.11
     extract
    0.11
    æĿ¥æºIJ
    0.11
    derived
    0.10
     processed
    0.10
    processed
    0.10
    ä¸ŃæıIJåıĸ
    0.10
    æıIJåıĸçī©
    0.10
    -based
    0.10
    Activations Density 0.307%

    No Known Activations