© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    specifically in this case

    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
    getOption
    -0.07
    è¦ģä¸įè¦ģ
    -0.07
    大ä¸ĸçķĮ
    -0.07
    lott
    -0.06
    engt
    -0.06
    åı¯æĺ¯ä¸Ģ
    -0.06
    æĹŃ
    -0.06
     Leh
    -0.06
    adata
    -0.06
    erat
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.20
    å°¤åħ¶
    0.12
    尤为
    0.11
     appunto
    0.10
     specifically
    0.10
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
    为ä¾ĭ
    0.09
     Specifically
    0.09
    áĢ·
    0.09
     particolar
    0.09
    Activations Density 0.682%

    No Known Activations