© 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. 58549
    Prev
    Next
    INDEX
    Explanations

    assertion and testing code

    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
    éij
    -0.08
    å¾ĹéĿŀ常
    -0.07
    æĪijçļĦè¯Ŀ
    -0.07
     varsa
    -0.07
    ech
    -0.07
    æĺ¾å¾ĹæĽ´åĬł
    -0.07
    emberg
    -0.07
    éľĢè¦ģä¸Ģ个
    -0.07
    éĥ½è¡Į
    -0.07
    éľĢè¦ģä»Ģä¹Ī
    -0.06
    POSITIVE LOGITS
    _correct
    0.07
     correct
    0.07
    _BOTH
    0.07
     correctly
    0.07
     pretty
    0.07
    aday
    0.07
    濯
    0.07
    é¢ĦæľŁ
    0.07
     confirming
    0.06
     rightly
    0.06
    Activations Density 0.042%

    No Known Activations