© 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. 33571
    Prev
    Next
    INDEX
    Explanations

    projected DTO, output, request

    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
    Ïģθ
    -0.08
    _Source
    -0.07
    .googlecode
    -0.07
     Reviewed
    -0.07
    stad
    -0.07
    anf
    -0.07
    obel
    -0.07
    ä¸įèµ·æĿ¥
    -0.07
    æĿ¥åİĨ
    -0.07
    textInput
    -0.07
    POSITIVE LOGITS
    è¾ĵåĩº
    0.10
    è¾ĵåĩºçļĦ
    0.10
     output
    0.10
     outputs
    0.10
     desired
    0.09
    -request
    0.09
    Output
    0.09
     requested
    0.09
    output
    0.09
    .output
    0.09
    Activations Density 0.134%

    No Known Activations