© 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. 8528
    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
    urch
    -0.08
    elli
    -0.08
    å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.07
    ä¸įä¸ĭ
    -0.07
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    æĺ¯åħ¶
    -0.07
    ÑĥÑĤа
    -0.07
    ritto
    -0.07
    ׼×ķת
    -0.07
    ÑĢÑĥм
    -0.06
    POSITIVE LOGITS
    ç®ĹäºĨ
    0.07
    欣çĦ¶
    0.07
    åij¦
    0.07
    被åĪĹåħ¥
    0.06
    rossover
    0.06
    ụng
    0.06
    Fn
    0.06
    zyd
    0.06
    aba
    0.06
    åĭ¤å¥ĭ
    0.06
    Activations Density 0.000%

    No Known Activations