© 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. 47431
    Prev
    Next
    INDEX
    Explanations

    instead of what I get

    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
    æŀī
    -0.07
    rous
    -0.07
    ilig
    -0.07
    lif
    -0.07
    èģĮå®Ī
    -0.07
    ãn
    -0.07
    ä¹Łæĺ¯åı¯ä»¥
    -0.06
     Darwin
    -0.06
     duly
    -0.06
    ä¸įåIJ¬
    -0.06
    POSITIVE LOGITS
     instead
    0.10
     malah
    0.09
     вмеÑģÑĤо
    0.08
     merely
    0.08
     Instead
    0.08
     Worse
    0.07
    åıįèĢĮ
    0.07
    instead
    0.07
    å±ħçĦ¶æĺ¯
    0.07
     دادÙĨ
    0.07
    Activations Density 0.365%

    No Known Activations