© 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. 43209
    Prev
    Next
    INDEX
    Explanations

    times greater, faster, higher, multiplication, smarter

    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
    sWith
    -0.10
    sök
    -0.08
    scheid
    -0.08
    anson
    -0.08
    Ĩµ
    -0.08
    licenses
    -0.08
    ught
    -0.07
    sse
    -0.07
    reibungen
    -0.07
    egos
    -0.07
    POSITIVE LOGITS
     lipat
    0.09
    å·¦åı³çļĦ
    0.08
    ponder
    0.08
    åĦ¿çļĦ
    0.08
    itarian
    0.08
     nhau
    0.07
    it
    0.07
    اÙĭ
    0.07
    vu
    0.07
    ãĤĪãģĨãģª
    0.07
    Activations Density 0.040%

    No Known Activations