© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57075
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    udo
    -0.08
    opr
    -0.07
    able
    -0.07
     напÑĢа
    -0.07
    erea
    -0.07
    ÑīеÑĤ
    -0.07
    ุà¸Ķ
    -0.07
    ABLE
    -0.07
    ugel
    -0.06
    UD
    -0.06
    POSITIVE LOGITS
     fanta
    0.07
    æľīçĹħ
    0.07
    /bind
    0.07
    å¾IJå¾IJ
    0.06
    asil
    0.06
    scy
    0.06
    Specifier
    0.06
    öld
    0.06
     ies
    0.06
    колÑĮ
    0.06
    Activations Density 0.007%

    No Known Activations