© 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. 33323
    Prev
    Next
    INDEX
    Explanations

    phase transition

    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
    ç¥ŀä¹ĭ
    -0.07
    elem
    -0.07
    amba
    -0.07
    æĽ´æĺ¯åľ¨
    -0.07
     Protected
    -0.07
    ogr
    -0.07
    icter
    -0.07
    eval
    -0.07
     protected
    -0.06
     innoc
    -0.06
    POSITIVE LOGITS
     discrete
    0.08
     muka
    0.08
    离æķ£
    0.07
     overwhelming
    0.07
     ÐŀÑĦоÑĢм
    0.07
     (>
    0.07
     Crate
    0.07
    åĪ«è¯´
    0.07
     overd
    0.06
    ä¼ĺ
    0.06
    Activations Density 0.001%

    No Known Activations