© 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. 34381
    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
    긴
    -0.08
    ê¸ī
    -0.07
    stup
    -0.07
    èµ°è·¯
    -0.07
    ëĭ¤ê°Ģ
    -0.07
    aroo
    -0.07
    æĵ¦å¹²
    -0.07
    aline
    -0.07
    佼佼
    -0.07
    åħ¬åı¸ä»ĭç»į
    -0.07
    POSITIVE LOGITS
    éĹ¹
    0.08
    å¨ĺ
    0.07
     Actress
    0.07
    å¨Ł
    0.06
    ä»ĺ
    0.06
    hana
    0.06
    b
    0.06
    èĩªèº«çļĦ
    0.06
    spo
    0.06
    igl
    0.06
    Activations Density 0.000%

    No Known Activations