© 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. 8473
    Prev
    Next
    INDEX
    Explanations

    vehicle parts and components

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    èĢĮéĿŀ
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
     pula
    -0.07
    没æľīåĩºçİ°
    -0.06
    èµĦæºIJ丰å¯Į
    -0.06
     arrang
    -0.06
    uring
    -0.06
    å¤§æľ¬
    -0.06
    _APPEND
    -0.06
    好åķĬ
    -0.06
    POSITIVE LOGITS
     altogether
    0.16
     anymore
    0.12
    顾ä¹ĭ忧
    0.12
    åİŁæľīçļĦ
    0.11
     khá»ıi
    0.10
    ä»»ä½ķ责任
    0.10
    以åħįå½±åĵį
    0.10
     entirely
    0.09
    alto
    0.09
    ä¹Łä¸įåĨį
    0.09
    Activations Density 0.433%

    No Known Activations