© 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. 11628
    Prev
    Next
    INDEX
    Explanations

    already implemented or satisfied

    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
    endan
    -0.08
    erar
    -0.08
    sr
    -0.07
    Serialized
    -0.07
    xab
    -0.07
    leos
    -0.07
     rost
    -0.07
    YSIS
    -0.07
    -repeat
    -0.07
     berani
    -0.07
    POSITIVE LOGITS
     sufficient
    0.07
     lah
    0.07
     suffis
    0.07
     suff
    0.07
    ufficient
    0.07
    æĹłéľĢ
    0.07
    ä¸ĩäºĭ
    0.07
    è¶³å¤ŁäºĨ
    0.07
     satisfactory
    0.06
    ukup
    0.06
    Activations Density 0.067%

    No Known Activations