© 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. 49515
    Prev
    Next
    INDEX
    Explanations

    websites ending in .com

    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
    交æĺĵä¼ļ
    -0.08
    _checker
    -0.08
     aka
    -0.08
    طة
    -0.07
    getJSON
    -0.07
    çī§
    -0.07
    æ¾Ī
    -0.07
    Checker
    -0.07
    ç³»ç»ŁåıĬ
    -0.07
    CDATA
    -0.07
    POSITIVE LOGITS
    å¹´é¾Ħ段
    0.06
    åĽ½è´¸
    0.06
    lew
    0.06
    建æĸ°
    0.06
    dyn
    0.06
     spo
    0.06
    浦
    0.06
    spo
    0.06
    çĩİ
    0.06
     fus
    0.06
    Activations Density 0.007%

    No Known Activations