© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23481
    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
     Chatt
    -0.08
    ers
    -0.07
    åįķæĭĽ
    -0.07
    BIND
    -0.07
    祸
    -0.07
     crim
    -0.07
    ICY
    -0.07
    <|repo_name|>
    -0.07
     Postar
    -0.07
    åģļå¾ĹæĽ´å¥½
    -0.07
    POSITIVE LOGITS
    owell
    0.09
    orts
    0.07
    ä¼ļæĻ¤
    0.06
    alom
    0.06
    èĪĪ
    0.06
    hirt
    0.06
    æ±ĩæĢ»è¡¨
    0.06
    çĮĽè¿Ľ
    0.06
    åİĨåİĨ
    0.06
    ä¼ļéĿ¢
    0.06
    Activations Density 0.000%

    No Known Activations