© 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. 47161
    Prev
    Next
    INDEX
    Explanations

    measuring markings and indicators

    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
    åħľ
    -0.09
    åŃ
    -0.08
    /ay
    -0.08
    undes
    -0.08
     пакеÑĤ
    -0.07
    软çļĦ
    -0.07
    éĿ¢éĿ¢
    -0.07
    à¸ŀั
    -0.07
    æĬī
    -0.07
    ronym
    -0.07
    POSITIVE LOGITS
    åĪ»åº¦
    0.13
    读æķ°
    0.10
     markings
    0.10
     gradu
    0.09
     ÑĪка
    0.09
     engraved
    0.09
    éĩıç¨ĭ
    0.08
    ÑĪка
    0.08
     readings
    0.08
    表çĽĺ
    0.08
    Activations Density 0.024%

    No Known Activations