© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42586
    Prev
    Next
    INDEX
    Explanations

    maximal peak response

    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
    pozy
    -0.07
    ulis
    -0.07
    ughter
    -0.07
    éģĵéģĵ
    -0.06
    å¿«å¿«
    -0.06
    κή
    -0.06
    豪
    -0.06
    å¿«çļĦ
    -0.06
    ç´¯çļĦ
    -0.06
    åįĩ级
    -0.06
    POSITIVE LOGITS
    æľĢä½³
    0.15
     optimum
    0.15
    æľĢä½³çļĦ
    0.14
     maximizing
    0.14
    æľĢ大
    0.14
    çļĦæľĢä½³
    0.14
     maxim
    0.14
     maximal
    0.14
     peak
    0.14
    æľĢ大åĮĸ
    0.14
    Activations Density 0.100%

    No Known Activations