© 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. 9934
    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
    ç©¿
    -0.07
    ince
    -0.07
     “
    -0.07
    usher
    -0.07
    (IB
    -0.06
    纵åIJij
    -0.06
    unks
    -0.06
    raid
    -0.06
    “
    -0.06
    横åIJij
    -0.06
    POSITIVE LOGITS
    å±ħçĦ¶
    0.09
    å±ħçĦ¶æĺ¯
    0.08
    äºĮæĿ¥
    0.08
    skyl
    0.07
    带ç»ĻæĪij们
    0.07
    è¿Ļ家ä¼Ļ
    0.07
    -related
    0.07
    erschaft
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    å¾·æĭī
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.