© 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. 40280
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    preter
    -0.08
    ãĢħ
    -0.07
    æĹłæģĻ
    -0.07
    kirchen
    -0.07
    alah
    -0.07
    asm
    -0.07
    czo
    -0.07
     dic
    -0.07
     |_|
    -0.07
    lys
    -0.06
    POSITIVE LOGITS
    odore
    0.07
    代为
    0.07
    éĿŀæ³ķ
    0.07
     scrim
    0.07
    å¹½
    0.07
    atória
    0.07
    å¸Ĩ
    0.06
    _launcher
    0.06
    人家çļĦ
    0.06
    代çIJĨ
    0.06
    Activations Density 0.081%

    No Known Activations