© 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. 43039
    Prev
    Next
    INDEX
    Explanations

    perturbation

    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
    erop
    -0.09
    /or
    -0.09
    ways
    -0.09
    ward
    -0.08
    ernen
    -0.08
    bouw
    -0.08
    ividual
    -0.08
    er
    -0.08
    ë£Į
    -0.08
    aner
    -0.08
    POSITIVE LOGITS
    urbed
    0.10
    å¼ĢæĿ¥
    0.08
    urbation
    0.08
    acular
    0.08
    atively
    0.08
    Occurred
    0.07
    ми
    0.07
    tida
    0.07
    -free
    0.07
    araf
    0.07
    Activations Density 0.008%

    No Known Activations