© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2988
    Prev
    Next
    INDEX
    Explanations

    conclusion indicators

    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
    缴æݥ就
    -0.08
    enci
    -0.08
    uvé
    -0.07
    ĵ
    -0.07
    arter
    -0.07
    _guard
    -0.07
    ulence
    -0.07
     Noble
    -0.07
    å°±è¿Ļä¹Ī
    -0.07
    éĽªçĻ½çļĦ
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯
    0.08
     might
    0.08
     suggest
    0.08
    æĪij认为
    0.08
     likely
    0.08
     Probably
    0.07
     probably
    0.07
    å¾Īåı¯èĥ½
    0.07
     could
    0.07
     peut
    0.07
    Activations Density 0.003%

    No Known Activations