© 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. 38003
    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
    æ±²
    -0.07
    lan
    -0.06
    -0.06
    ABA
    -0.06
     ker
    -0.06
     Paw
    -0.06
     lÆ°u
    -0.06
     ÙĦÙĦا
    -0.06
    åħ¸
    -0.06
    ивно
    -0.06
    POSITIVE LOGITS
    غاÙħ
    0.08
    ÏĨÏħ
    0.08
    enci
    0.08
    å¾ĹçĽĬ
    0.08
    åı¯ä»¥æĶ¾å¿ĥ
    0.07
    anse
    0.07
    ุà¸Ķ
    0.07
    èĩªè¾¾
    0.07
    å±±æ¹ĸ
    0.07
    èĩªå·±è¢«
    0.07
    Activations Density 0.000%

    No Known Activations