© 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. 33602
    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
    æķĻèĤ²ç½ij
    -0.08
    istrict
    -0.08
    京åħ¬ç½ijå®īå¤ĩ
    -0.07
    æµİ
    -0.07
    ×ķ×ķת
    -0.07
    oten
    -0.07
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    éĤ£åı¯
    -0.07
    -import
    -0.07
    ç»ĵåIJĪå®ŀéĻħ
    -0.07
    POSITIVE LOGITS
    uish
    0.07
    quoi
    0.07
    สำ
    0.07
    ç²±
    0.07
    åĭŁ
    0.07
    fusc
    0.06
    ottage
    0.06
     optimizer
    0.06
    æݧåĪ¶åı°
    0.06
     Rise
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.