© 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. 29579
    Prev
    Next
    INDEX
    Explanations

    width and alignment

    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
    åĴĮåŃ¦ä¹ł
    -0.07
    Vertical
    -0.07
    åĢĴäºĨ
    -0.07
    æĢ»éĺŁ
    -0.07
     tallest
    -0.07
    çŃĴ
    -0.07
     Vertical
    -0.07
     [[[
    -0.06
     vertical
    -0.06
    enstein
    -0.06
    POSITIVE LOGITS
    wide
    0.10
    panse
    0.09
     horizontally
    0.09
     horizont
    0.08
     wide
    0.08
    éĵºè®¾
    0.08
    -wide
    0.08
    横åIJij
    0.08
    -width
    0.08
    å¹³
    0.08
    Activations Density 0.059%

    No Known Activations