© 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. 33742
    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
    大åħ¸
    -0.08
    æĬĬå®ĥ们
    -0.07
    XHR
    -0.07
    deaux
    -0.07
    å»ī
    -0.07
    à¸Ľà¸Ľ
    -0.07
    å°ı红书
    -0.07
    angen
    -0.07
     Obr
    -0.06
    lisi
    -0.06
    POSITIVE LOGITS
    ursa
    0.08
    缸æī£
    0.07
    але
    0.07
     Wig
    0.07
    HEMA
    0.07
    æİ¥
    0.07
    ç»ĵæŀľä¸º
    0.07
     Gomez
    0.07
     results
    0.06
    æİ¥åĪ°
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.