© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46566
    Prev
    Next
    INDEX
    Explanations

    @Id class

    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
    ä¹Łè®¸ä¼ļ
    -0.08
     maybe
    -0.08
    éļ¾åħį
    -0.08
    å°±åı¯èĥ½
    -0.08
    æĢ§æĪĸ
    -0.08
    èĻ½æĺ¯
    -0.07
    ä¹Łåı¯èĥ½
    -0.07
    åĪĻåı¯
    -0.07
    åı¯èĥ½éľĢè¦ģ
    -0.07
    ä¹Łè®¸
    -0.07
    POSITIVE LOGITS
     sogenannten
    0.10
     sogenannte
    0.09
     sogen
    0.09
     infatti
    0.08
    çŃĶæ¡Ī解æŀIJ
    0.08
    bÄĽ
    0.07
     cosidd
    0.07
    ãģĦãĤıãĤĨãĤĭ
    0.07
     famously
    0.07
     assolutamente
    0.07
    Activations Density 0.019%

    No Known Activations