© 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. 45573
    Prev
    Next
    INDEX
    Explanations

    ? or !

    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
    .attrs
    -0.09
    æĪĸå¤ļ个
    -0.09
    stile
    -0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    /XMLSchema
    -0.08
    夫æĸ¯åŁº
    -0.08
     irgendwie
    -0.08
    ierer
    -0.08
    (or
    -0.08
    icket
    -0.08
    POSITIVE LOGITS
    ing
    0.07
    ãĤĵãģ³
    0.07
    ens
    0.06
    -know
    0.06
    asi
    0.06
    iel
    0.06
    èĢĮçŁ¥
    0.06
    oj
    0.06
    inger
    0.05
    he
    0.05
    Activations Density 0.004%

    No Known Activations