© 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. 39728
    Prev
    Next
    INDEX
    Explanations

    php code structure

    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
    ude
    -0.08
    ute
    -0.07
    lej
    -0.07
    imo
    -0.07
     Guz
    -0.07
    å±ı
    -0.07
    天å®ī
    -0.07
    åijľ
    -0.07
    rone
    -0.07
    ä¸ĭä¸Ģç«ł
    -0.07
    POSITIVE LOGITS
    çĻ»è®°
    0.07
    .attr
    0.07
    ни
    0.06
    çļĦæ°´æ³¥
    0.06
    éģĵ
    0.06
    resenter
    0.06
    онеÑĢ
    0.06
    andre
    0.06
    ems
    0.06
     fullname
    0.06
    Activations Density 0.020%

    No Known Activations