© 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. 9440
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    помина
    -0.09
    λικ
    -0.09
    iago
    -0.09
    полни
    -0.08
    erima
    -0.08
    erar
    -0.08
    ousse
    -0.08
    подоб
    -0.08
    er
    -0.08
    зади
    -0.08
    POSITIVE LOGITS
    /out
    0.09
     negeri
    0.08
    bur
    0.07
    /to
    0.07
    /on
    0.07
    -
    0.07
    ilter
    0.07
    æĿ¥å¾ĹåıĬ
    0.07
    ag
    0.07
     sheer
    0.06
    Activations Density 0.057%

    No Known Activations