© 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. 65364
    Prev
    Next
    INDEX
    Explanations

    specific names, locations, or abbreviations

    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
    enos
    -0.09
    å¹´å¢ŀéķ¿
    -0.08
    éal
    -0.08
    æī¬æī¬
    -0.08
    æĭ¿åĩºæĿ¥
    -0.08
    åĽłäºº
    -0.08
    åĬªåĬĽä¸ĭ
    -0.08
    nalis
    -0.07
    >false
    -0.07
    cula
    -0.07
    POSITIVE LOGITS
    olio
    0.07
    åģ¶
    0.06
    .consume
    0.06
    ç·¯
    0.06
    ...
    0.06
    å¾ħ
    0.06
    ullet
    0.06
    (...)
    0.06
    æŃ£å¼ı
    0.06
    åĬĽæ±Ĥ
    0.06
    Activations Density 0.012%

    No Known Activations