© 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. 22272
    Prev
    Next
    INDEX
    Explanations

    geometric intersection points

    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
    ä¸įèĥ½è®©
    -0.09
    路西
    -0.08
    eix
    -0.08
    ä¸ĢåĪĩçļĦ
    -0.08
    kali
    -0.08
     +'
    -0.08
    cher
    -0.08
    worth
    -0.08
    ÑĪев
    -0.08
    对çݯå¢ĥ
    -0.08
    POSITIVE LOGITS
     somewhere
    0.08
    以确å®ļ
    0.07
     via
    0.07
    å½¢æĪIJä¸Ģ个
    0.06
    å½¢æĪIJäºĨ
    0.06
     Continent
    0.06
    ymes
    0.06
     earlier
    0.06
    è®°ä¸ĭ
    0.06
    润
    0.06
    Activations Density 0.005%

    No Known Activations