© 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. 31568
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    noinspection
    -0.09
    گذارÛĮ
    -0.09
    umon
    -0.08
    å¦ĤæŀľåĨį
    -0.08
    ubby
    -0.07
    满
    -0.07
     ------------------------------------------------------------------------------------------------
    -0.07
    Ĵ¤
    -0.07
    ==$
    -0.07
    пÑĢоÑĨе
    -0.07
    POSITIVE LOGITS
    æ³
    0.08
    __:
    0.07
    alh
    0.07
    ia
    0.07
    ÃŃa
    0.07
     `
    0.06
    axe
    0.06
    sy
    0.06
    haw
    0.06
    usa
    0.06
    Activations Density 0.000%

    No Known Activations