© 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. 64791
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     <<-
    -0.08
    /cms
    -0.07
    alit
    -0.07
     prom
    -0.06
     vite
    -0.06
    .$.
    -0.06
     voire
    -0.06
     overriding
    -0.06
     &$
    -0.06
    fbe
    -0.06
    POSITIVE LOGITS
    èĤļ
    0.08
    æ¤į
    0.08
    kens
    0.08
    å¤ļä¸Ģ份
    0.07
    ŃIJ
    0.07
    enni
    0.07
    à°¿à°Ĥà°ļ
    0.07
    prud
    0.07
    èijĨ
    0.07
    bum
    0.07
    Activations Density 0.003%

    No Known Activations