© 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. 10165
    Prev
    Next
    INDEX
    Explanations

    way toway of

    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
    ä¸įèĥ½æľī
    -0.08
    igel
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
    ä¸įèĥ½ä½ľä¸º
    -0.07
    inki
    -0.07
    æ¯
    -0.07
    å¦ĤåIJĮä¸Ģ
    -0.07
    plain
    -0.07
    ä¸įæĥľ
    -0.06
    åıªåľ¨
    -0.06
    POSITIVE LOGITS
    æĹ¢
    0.10
    æĹ¢æľī
    0.09
    iha
    0.08
    å®ĥä¸įä»ħ
    0.08
    满足äºĨ
    0.08
     olacaktır
    0.08
    æĹ¢åı¯
    0.08
     hopefully
    0.08
    åıĪéģĵ
    0.08
    æĬĵä½ıäºĨ
    0.07
    Activations Density 0.007%

    No Known Activations