© 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. 8015
    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
    resh
    -0.08
     Lô
    -0.08
    _ENCODE
    -0.07
     ÑģанÑĤим
    -0.07
    zeh
    -0.07
    çł¥çłºåīįè¡Į
    -0.07
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.07
    istante
    -0.07
    наÑĩа
    -0.07
    ä¸įæ±Ĥ
    -0.07
    POSITIVE LOGITS
    astos
    0.07
     distr
    0.07
    å±ĭéĩĮ
    0.07
    âĢ¦but
    0.07
    odos
    0.07
     pract
    0.06
    âĢ¦and
    0.06
    æĸ¯åħĭ
    0.06
    Nos
    0.06
     Nos
    0.06
    Activations Density 0.000%

    No Known Activations