© 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. 60594
    Prev
    Next
    INDEX
    Explanations

    's, ism, or proper nouns

    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
    obiet
    -0.08
    ilty
    -0.08
    itions
    -0.08
     ÐŁÐ¾Ð¿ÑĢо
    -0.08
    åħĭåĬĽ
    -0.07
    icking
    -0.07
     á»ijc
    -0.07
     './../
    -0.07
    obilier
    -0.07
    :create
    -0.07
    POSITIVE LOGITS
    ละ
    0.07
    _bit
    0.07
    ques
    0.06
    缮
    0.06
    raq
    0.06
    íĥģ
    0.06
    稼
    0.06
    缸
    0.06
     conclus
    0.06
    åıĸ
    0.06
    Activations Density 0.029%

    No Known Activations