© 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. 27824
    Prev
    Next
    INDEX
    Explanations

    representation and permutation theory

    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
    åħī顾
    -0.07
     Sido
    -0.07
    obel
    -0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    -0.07
    åĬªåĬĽåŃ¦ä¹ł
    -0.07
    apore
    -0.06
    åĨĴåĩº
    -0.06
    ิà¸Ļ
    -0.06
    ä¸Ĭè¿Ľå¿ĥ
    -0.06
    olet
    -0.06
    POSITIVE LOGITS
     faithful
    0.09
    /embed
    0.08
    äºĨä¸Ģå¥Ĺ
    0.08
     faithfully
    0.08
    å¿łå®ŀ
    0.08
    URLRequest
    0.07
     representation
    0.07
    åIJĮå·¥
    0.07
    åĪ°ä½į
    0.07
    otypical
    0.07
    Activations Density 0.010%

    No Known Activations