© 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. 47704
    Prev
    Next
    INDEX
    Explanations

    open-and-shut, multiplicative, catered, commonly, very poor, null, regex, world

    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
    onnier
    -0.09
    äºĮä¸ĸ
    -0.09
    cados
    -0.08
    udit
    -0.08
    atia
    -0.08
    ikin
    -0.08
    enders
    -0.08
    /DD
    -0.08
    WithData
    -0.07
    zinha
    -0.07
    POSITIVE LOGITS
     [
    0.06
     somehow
    0.06
     sogenannten
    0.06
    agar
    0.06
    Âł
    0.06
     supposedly
    0.06
    ...
    0.06
    âĢ
    0.06
     Jar
    0.05
    é¦Ļ
    0.05
    Activations Density 0.154%

    No Known Activations