© 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. 63284
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving intervals and derivatives

    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
    æ±°
    -0.07
    é¸¡æ¯Ľ
    -0.07
    rex
    -0.07
    avion
    -0.07
    å½¼æѤçļĦ
    -0.07
    geo
    -0.06
    æĬĺä¸įæī£
    -0.06
    ôs
    -0.06
    entif
    -0.06
    æľ¬æĸĩçĶ±
    -0.06
    POSITIVE LOGITS
    ungi
    0.07
    .fac
    0.07
    å¼Ģåı£éģĵ
    0.07
    çĬ¯
    0.07
    INU
    0.07
    AGO
    0.07
    åĽ¢æĪĺ
    0.07
    æĪijä¹Łåİ»çŃĶé¢ĺ
    0.07
     Bullet
    0.07
    rollo
    0.07
    Activations Density 0.004%

    No Known Activations