© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10865
    Prev
    Next
    INDEX
    Explanations

    counting numbers

    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
    etem
    -0.08
    arder
    -0.07
    asma
    -0.07
    bonne
    -0.07
    éĻIJãĤĬ
    -0.07
     Rhe
    -0.06
    emean
    -0.06
    toPromise
    -0.06
     interp
    -0.06
    tele
    -0.06
    POSITIVE LOGITS
     counting
    0.13
    æĢ»æķ°çļĦ
    0.12
    æĢ»æķ°
    0.12
    计æķ°
    0.11
     counts
    0.11
    .count
    0.11
     counted
    0.10
     Äijếm
    0.10
     enumer
    0.10
    è¿Ļ个æķ°åŃĹ
    0.10
    Activations Density 0.025%

    No Known Activations