© 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. 42907
    Prev
    Next
    INDEX
    Explanations

    code context and identifiers

    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
     <<=
    -0.06
    orman
    -0.06
     ($)
    -0.06
    âĢ¦âĢ¦ãĢĤ
    -0.06
     Flint
    -0.06
    æĪijæĥ³è¦ģ
    -0.06
    Offline
    -0.06
    ä¹ŁæľīæīĢ
    -0.06
    æľīæīĢ
    -0.06
    .Reporting
    -0.06
    POSITIVE LOGITS
     ndr
    0.08
    飵
    0.07
    éŃĤ
    0.07
    åĪĨéĻ¢
    0.07
    detail
    0.07
    reeze
    0.07
     Entret
    0.07
    xba
    0.07
     cias
    0.07
    ellen
    0.07
    Activations Density 0.090%

    No Known Activations