© 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. 49653
    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
    çħ§æł·
    -0.08
    åĵģç§į
    -0.06
     ervoor
    -0.06
    æŃ»æ´»
    -0.06
    è¿Ļåı«
    -0.06
     everybody
    -0.06
     invisible
    -0.06
    zyw
    -0.06
     scheduled
    -0.06
    åĽºå®ļåľ¨
    -0.06
    POSITIVE LOGITS
    æľĢèĥ½
    0.09
    æľĢä½³çŃĶæ¡Ī
    0.09
    è¾ĥ为
    0.09
     наиболее
    0.08
    emain
    0.08
    çŃī主è¦ģ
    0.08
    osat
    0.08
    ĥĿ
    0.08
    æľĢåħ·
    0.08
     наиб
    0.08
    Activations Density 0.000%

    No Known Activations