© 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. 22411
    Prev
    Next
    INDEX
    Explanations

    regex query rule mapping suit

    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
    adis
    -0.08
    ucks
    -0.08
    ès
    -0.07
    åħ¶ä¸Ģ
    -0.07
    asto
    -0.07
     pragma
    -0.07
    æ¢ĵ
    -0.07
    干湿
    -0.07
    thenReturn
    -0.07
    碧çİī
    -0.07
    POSITIVE LOGITS
     proposed
    0.09
     supposed
    0.08
     proposée
    0.08
    å±ħçĦ¶
    0.08
    æĭŁ
    0.07
     Proposed
    0.07
     predicted
    0.07
     allegedly
    0.07
     formula
    0.07
    åħ¬å¼ı
    0.07
    Activations Density 0.007%

    No Known Activations