© 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. 50400
    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
    _pagination
    -0.07
    edig
    -0.07
    åħĪå¾Ĺ
    -0.07
    æľ¬æĸĩçĶ±
    -0.07
    æį®
    -0.07
     ngo
    -0.07
    åħĪåĪ°
    -0.06
    unga
    -0.06
    agua
    -0.06
    欢ç¬ij
    -0.06
    POSITIVE LOGITS
    isci
    0.07
    åħ¶ä»ĸåªĴä½ĵ
    0.07
    åħ¶ä»ĸ
    0.07
    ä¸ĭä¸ĢæŃ¥
    0.07
    ä¸įåIJĮè§Ĵ度
    0.07
    åħ¶å®ĥ
    0.07
     подвод
    0.07
    åīįç¨ĭ
    0.07
    ös
    0.07
     mö
    0.07
    Activations Density 0.000%

    No Known Activations