© 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. 51559
    Prev
    Next
    INDEX
    Explanations

    number or quantity

    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
    omini
    -0.08
    zell
    -0.08
    ovn
    -0.08
    gmt
    -0.08
    æĦŁæĥħçļĦ
    -0.08
    wers
    -0.07
    éĻĪå¿Ĺ
    -0.07
    åĩºèµĦæĹ¥æľŁ
    -0.07
    iona
    -0.07
    chor
    -0.07
    POSITIVE LOGITS
     number
    0.12
     count
    0.11
    æĢ»æķ°
    0.11
    count
    0.10
    number
    0.10
     counting
    0.09
     Count
    0.09
    æķ°éĩı为
    0.09
     Anzahl
    0.09
    .count
    0.09
    Activations Density 0.077%

    No Known Activations