© 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. 31054
    Prev
    Next
    INDEX
    Explanations

    doi and citations

    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
    atest
    -0.08
    <![
    -0.08
    atti
    -0.08
    issing
    -0.08
    ساء
    -0.08
    ibo
    -0.08
    ä¹ħä¹ĭ
    -0.08
    iga
    -0.07
    综åIJĪåĪ©çĶ¨
    -0.07
    arak
    -0.07
    POSITIVE LOGITS
    ä¾ĭ
    0.07
     Townsend
    0.06
     Ernst
    0.06
    ayani
    0.06
     Milky
    0.06
     .
    0.06
    ä¸Ģåĩ»
    0.06
    人头
    0.06
     molt
    0.05
     Quinn
    0.05
    Activations Density 0.123%

    No Known Activations