© 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. 60812
    Prev
    Next
    INDEX
    Explanations

    amounts

    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
    &s
    -0.09
    alani
    -0.08
    æīįæľīäºĨ
    -0.08
    θή
    -0.08
    abel
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    ["$
    -0.07
    _formats
    -0.07
    )=='
    -0.07
    eltas
    -0.07
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.08
     fixed
    0.08
    unless
    0.08
    .Default
    0.07
     unless
    0.07
    astre
    0.07
    åİŁåĪĻä¸Ĭ
    0.07
     or
    0.07
    åĽºå®ļ
    0.07
    Activations Density 0.329%

    No Known Activations