© 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. 37989
    Prev
    Next
    INDEX
    Explanations

    seeking help or solution

    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
    uid
    -0.08
    è¶³å¤Ł
    -0.08
     adequate
    -0.07
    è¶³å¤ŁçļĦ
    -0.07
    mpl
    -0.07
     sufficient
    -0.06
     Dob
    -0.06
    urg
    -0.06
    åħħ足
    -0.06
    产ä¸ļæĶ¿çŃĸ
    -0.06
    POSITIVE LOGITS
    被å°ģ
    0.07
    acar
    0.07
    Locker
    0.07
     sedu
    0.07
    uha
    0.07
     dedu
    0.07
    Äŀ
    0.07
    å°ıä¼Ļ伴们
    0.07
    _BINDING
    0.07
    ÙıÙij
    0.07
    Activations Density 0.001%

    No Known Activations