© 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. 41948
    Prev
    Next
    INDEX
    Explanations

    documentation comments

    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
    ehren
    -0.09
    pst
    -0.08
    æg
    -0.07
    cura
    -0.07
    åºIJ
    -0.07
    è´¯
    -0.07
    Whatever
    -0.07
    halat
    -0.06
    (/*
    -0.06
    iros
    -0.06
    POSITIVE LOGITS
    ä¸Ģåıį
    0.07
    additional
    0.07
    åı¯éĢī
    0.07
    彦
    0.07
    æ´»
    0.07
    [out
    0.07
    碧海
    0.07
     additional
    0.07
    åĪº
    0.07
    [opt
    0.07
    Activations Density 0.042%

    No Known Activations