© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    local splits or graphs

    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
    erate
    -0.07
    ÑĤÑĢе
    -0.07
    缼
    -0.07
    iket
    -0.07
    طار
    -0.06
    iera
    -0.06
     Ùħعا
    -0.06
    婧
    -0.06
    dsn
    -0.06
     mobil
    -0.06
    POSITIVE LOGITS
    æŁIJäºĽ
    0.08
    åĮºåŁŁæĢ§
    0.07
     partial
    0.07
     portions
    0.07
    å¡ĮéĻ·
    0.07
    åı¯èĥ½å¯¼èĩ´
    0.07
    å±Ģéĥ¨
    0.07
    æĩĴ
    0.07
    issing
    0.07
    ainless
    0.07
    Activations Density 0.010%

    No Known Activations