© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    orris
    -0.08
     Ú©ÙĨ
    -0.08
     Frid
    -0.08
    ä¹ħä¹ĭ
    -0.07
    UEST
    -0.07
    à¸ĸ
    -0.07
    å¸Ĥæĸ°
    -0.07
    à¸Ŀ
    -0.07
    RunWith
    -0.07
    å¼Ĺåħ°
    -0.07
    POSITIVE LOGITS
     aufgeh
    0.08
    æ¶ĪéĻ¤
    0.08
    æľī为
    0.08
     eliminated
    0.07
    åıĸæ¶Ī
    0.07
     canc
    0.07
    æ¶ĪçģŃ
    0.07
     cancelled
    0.07
     cancel
    0.07
    æ¶ħ
    0.07
    Activations Density 0.010%

    No Known Activations