© 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. 2813
    Prev
    Next
    INDEX
    Explanations

    name == "name"

    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
    路费
    -0.06
    çĨ
    -0.06
    åįģåĪĨ
    -0.06
    å
    -0.06
    éĽ
    -0.05
    à¹ĩม
    -0.05
    amen
    -0.05
    管
    -0.05
    starter
    -0.05
    VERTISE
    -0.05
    POSITIVE LOGITS
    ä¹Ķ丹
    0.08
    enes
    0.07
    åĽ¢çļĦ
    0.07
    åĭĴæĸ¯
    0.07
    ibo
    0.07
    å·´æĭī
    0.07
    igel
    0.07
    новÑĢемен
    0.07
    çī©æµģä¸Ńå¿ĥ
    0.07
    sour
    0.07
    Activations Density 0.482%

    No Known Activations