© 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. 33622
    Prev
    Next
    INDEX
    Explanations

    although, though

    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¸įä»ħåľ¨
    -0.08
    æĿIJæĸĻåıĬ
    -0.08
    åĪĻæĺ¯
    -0.08
    éĻ¤äºĨæľī
    -0.08
    ä¸įä½Ĩ
    -0.07
    èĩ³å°ij
    -0.07
    èĻ½çĦ¶æ²¡æľī
    -0.07
    jenigen
    -0.07
     invece
    -0.07
    ä¸įä»ħ
    -0.07
    POSITIVE LOGITS
     technically
    0.11
    çľĭä¼¼
    0.10
    ãģ¾ãģĽãĤĵãģĮ
    0.10
    âĢ¦),
    0.09
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    0.09
    à¸ģà¹ĩà¸ķาม
    0.09
    ä¸įèĥ½å®Įåħ¨
    0.09
    :],
    0.09
     theoretically
    0.08
    **),
    0.08
    Activations Density 0.427%

    No Known Activations