© 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. 11440
    Prev
    Next
    INDEX
    Explanations

    quantities followed by units (/kg, /ml, g)

    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
    åĬłæĭī
    -0.06
    åİ¿
    -0.06
    ekk
    -0.06
     spont
    -0.06
    arre
    -0.06
     seno
    -0.06
    è§ī
    -0.06
    è°´
    -0.06
    odr
    -0.06
    çİ°å®ŀæĦıä¹ī
    -0.06
    POSITIVE LOGITS
     Secondary
    0.08
     secondary
    0.07
    鬼çİĭ
    0.07
    enate
    0.07
    ronic
    0.07
    ctal
    0.07
    upert
    0.07
    semble
    0.07
    aravel
    0.07
    -primary
    0.07
    Activations Density 0.034%

    No Known Activations