© 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. 22701
    Prev
    Next
    INDEX
    Explanations

    discussion of issues or solutions

    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
    å®ĥå°±æĺ¯
    -0.08
    itled
    -0.07
    à¸Ħà¹Į
    -0.07
    auled
    -0.07
    çļĦåĵģè´¨
    -0.07
    å¿ħé¡»åħ·å¤ĩ
    -0.07
    åĴĮä¸įèī¯
    -0.06
    תר
    -0.06
    orra
    -0.06
    رد
    -0.06
    POSITIVE LOGITS
    fully
    0.07
    å¸ģ
    0.06
    programm
    0.06
    xor
    0.06
    ame
    0.06
    chemistry
    0.06
    ussen
    0.06
    äch
    0.06
    èµ·æĿ¥äºĨ
    0.06
    fatt
    0.06
    Activations Density 0.157%

    No Known Activations