© 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. 40607
    Prev
    Next
    INDEX
    Explanations

    matrices, text, lists, sequences

    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
    (tm
    -0.07
     kele
    -0.07
    çĥ¨
    -0.07
    æľĪä¸Ĭ
    -0.07
    kem
    -0.07
    ogue
    -0.06
    çļĭ
    -0.06
    à¸į
    -0.06
    éĿĴçĿIJ
    -0.06
    immel
    -0.06
    POSITIVE LOGITS
    нÑı
    0.08
    å¿ħ须符åIJĪ
    0.07
    é¬
    0.07
    åħ¨ä½ĵ
    0.07
    resar
    0.07
    usy
    0.07
    æĢĿ
    0.07
    amise
    0.07
    人äºĭéĥ¨
    0.07
    å¦Ĥ鼨
    0.07
    Activations Density 0.034%

    No Known Activations