© 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. 22675
    Prev
    Next
    INDEX
    Explanations

    enabled, yes, true

    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
    æģ¶
    -0.07
    è¯
    -0.07
    versch
    -0.07
    æĭħå½ĵä½ľä¸º
    -0.07
    нÑĮ
    -0.07
    èĵ
    -0.07
     //'
    -0.06
    acus
    -0.06
    из
    -0.06
    peg
    -0.06
    POSITIVE LOGITS
     yes
    0.22
    åIJ¦
    0.19
     Yes
    0.19
    Yes
    0.19
     YES
    0.19
    yes
    0.18
    æĺ¯çļĦ
    0.17
    ä¸İåIJ¦
    0.17
     true
    0.17
     True
    0.16
    Activations Density 0.217%

    No Known Activations