© 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. 49235
    Prev
    Next
    INDEX
    Explanations

    separates list items or clauses

    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
    ieu
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.08
    iber
    -0.08
    ÛĮز
    -0.07
    ówe
    -0.07
    åĽ½èĢĥ
    -0.07
    ütz
    -0.07
    å¹½
    -0.07
    olib
    -0.07
     bcm
    -0.07
    POSITIVE LOGITS
    åŁł
    0.07
    rades
    0.07
    æĺİçĻ½äºĨ
    0.07
    ossal
    0.06
     what
    0.06
    ..\
    0.06
    gili
    0.06
    ستگÛĮ
    0.06
    nder
    0.06
    gn
    0.06
    Activations Density 0.001%

    No Known Activations