© 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. 42929
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
     urn
    -0.06
    urrect
    -0.06
    allon
    -0.06
    ?url
    -0.06
     Envir
    -0.06
    mic
    -0.06
     inh
    -0.06
    äºĶ次
    -0.06
     Org
    -0.06
    mon
    -0.06
    POSITIVE LOGITS
    elde
    0.08
    ë¹Ļ
    0.08
    忱
    0.08
    æģ
    0.08
    ços
    0.08
    á»ijt
    0.08
    ensore
    0.07
     thâm
    0.07
    antal
    0.07
    elden
    0.07
    Activations Density 0.003%

    No Known Activations