© 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. 10040
    Prev
    Next
    INDEX
    Explanations

    app development, engagement ring, startup, fashion industry, skin treatments, sciatica, affiliate program

    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
    该åĮº
    -0.07
    æĬĺ
    -0.06
    åĮº
    -0.06
    /
    -0.06
    áĥĿáĥij
    -0.06
    i
    -0.06
    éħ·
    -0.06
    emit
    -0.06
    èĤī
    -0.06
    ASIC
    -0.06
    POSITIVE LOGITS
    å°¼æĸ¯
    0.08
    otar
    0.08
     moduleId
    0.07
    åĪĨ享èĩ³
    0.07
    addir
    0.07
    наÑĢ
    0.07
    ίδ
    0.07
    并éĿŀæĺ¯
    0.07
    -enabled
    0.07
    åĵ¥ä¼¦
    0.07
    Activations Density 0.006%

    No Known Activations