© 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. 62645
    Prev
    Next
    INDEX
    Explanations

    inwithasforusing

    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
    æĬĬå®ĥ
    -0.07
     jota
    -0.07
    วà¸Ļ
    -0.07
    à¸Ńà¸Ķี
    -0.07
    æĪijæĬĬ
    -0.06
    orph
    -0.06
    _defined
    -0.06
    å®ļä½įäºİ
    -0.06
    æĬĬè¿ĻäºĽ
    -0.06
    çĿĢèĩªå·±
    -0.06
    POSITIVE LOGITS
     oleh
    0.11
     تÙĪسط
    0.11
    /by
    0.11
     bợi
    0.11
     ÐĴами
    0.10
     вами
    0.10
    æĪĸçĶ±
    0.10
    leine
    0.10
     by
    0.10
     вÑĢаÑĩом
    0.09
    Activations Density 1.161%

    No Known Activations