© 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. 61511
    Prev
    Next
    INDEX
    Explanations

    normative specification

    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
    gether
    -0.10
    scape
    -0.08
    lukan
    -0.07
    gnore
    -0.07
    wards
    -0.07
    phine
    -0.07
    aurus
    -0.07
    å½Ĵæł¹
    -0.07
    gow
    -0.06
    efon
    -0.06
    POSITIVE LOGITS
    jš
    0.10
    atively
    0.10
    isht
    0.09
    ously
    0.09
    åĮĸçļĦ
    0.09
    rawdÄĻ
    0.09
    istros
    0.09
    æĢ§çļĦ
    0.09
    papier
    0.09
    èµ·è§ģ
    0.09
    Activations Density 0.015%

    No Known Activations