© 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. 28400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ij¸
    -0.08
    lag
    -0.08
    渤
    -0.08
    ä¹Ĵä¹ĵ
    -0.08
    UBLE
    -0.07
    裸
    -0.07
    èIJ½æ°´
    -0.07
    hlung
    -0.07
    incia
    -0.07
    è£¸éľ²
    -0.07
    POSITIVE LOGITS
     ratios
    0.12
     ratio
    0.10
     Ratio
    0.09
    æ¯Ķä¾ĭ
    0.09
    æ¯ĶåĢ¼
    0.09
    Ratio
    0.08
    ratio
    0.08
     proportion
    0.08
     proportional
    0.08
    æ¯Ķä¾ĭçļĦ
    0.08
    Activations Density 0.000%

    No Known Activations