© 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. 51115
    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
     (!
    -0.07
    isci
    -0.07
    erta
    -0.07
    getto
    -0.07
    kof
    -0.07
    ipun
    -0.07
    ä¸Ģåı¶
    -0.07
    åı¯æĢľ
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    loff
    -0.07
    POSITIVE LOGITS
    oup
    0.08
    roc
    0.07
    ëĿ½
    0.07
    apul
    0.06
    wander
    0.06
    sein
    0.06
     thang
    0.06
    omis
    0.06
    водов
    0.06
    ulse
    0.06
    Activations Density 0.000%

    No Known Activations