© 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. 32297
    Prev
    Next
    INDEX
    Explanations

    circ or Circ

    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
    eve
    -0.07
    ÏģÎŃ
    -0.07
    ypy
    -0.07
    valo
    -0.07
    æľĪçĶŁ
    -0.06
    év
    -0.06
     viu
    -0.06
    izzard
    -0.06
    veli
    -0.06
    ucas
    -0.06
    POSITIVE LOGITS
    溪éķĩ
    0.07
     circulated
    0.07
    uri
    0.07
     CALLBACK
    0.07
    ier
    0.07
    ä¹ĭäºĮ
    0.06
    åĪ¶éĢłæľīéĻIJåħ¬åı¸
    0.06
    circ
    0.06
     Circ
    0.06
     (*(
    0.06
    Activations Density 0.208%

    No Known Activations