© 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. 20522
    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
    alit
    -0.09
    uco
    -0.09
    ipot
    -0.08
    VERAGE
    -0.08
    à¤ľà¥ĩ
    -0.08
    pmat
    -0.08
    -caret
    -0.08
    ORAGE
    -0.08
    åŃĺåĤ¨æľįåĬ¡
    -0.08
    ä¹IJä¹İ
    -0.08
    POSITIVE LOGITS
    ä¸įåı¯éģ¿åħįçļĦ
    0.07
    èĩ£
    0.07
     irreversible
    0.07
    se
    0.07
     efficiency
    0.06
     dissip
    0.06
    æķĪçİĩ
    0.06
    å¤Ħå¤Ħ
    0.06
    为æݨåĬ¨
    0.06
    illard
    0.06
    Activations Density 0.000%

    No Known Activations