© 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. 22656
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions and elaborate remarks

    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
    ingin
    -0.08
    æľĢæĸ°æĽ´æĸ°
    -0.08
    é£Ļ
    -0.07
    æĢ»ä½ĵ
    -0.07
    imately
    -0.07
    antz
    -0.07
    à¸ģุม
    -0.07
    middel
    -0.07
    便è¦ģ
    -0.07
    UTO
    -0.07
    POSITIVE LOGITS
    ari
    0.06
    ä¸Ĭå½ĵ
    0.06
     gramm
    0.06
    .DateTime
    0.06
    ook
    0.06
    -notes
    0.06
    notes
    0.06
     sr
    0.06
    ular
    0.06
    fare
    0.06
    Activations Density 0.061%

    No Known Activations