© 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. 33444
    Prev
    Next
    INDEX
    Explanations

    radiation therapy and sources

    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
    ÙĬÙĨ
    -0.08
    ogh
    -0.07
    reet
    -0.07
    ×Ļ×Ļ×Ŀ
    -0.07
    .wikipedia
    -0.07
    ì§ĵ
    -0.07
    ÅĻ
    -0.07
    umul
    -0.07
    /disable
    -0.07
    бÑĥдÑĮ
    -0.07
    POSITIVE LOGITS
    uzzi
    0.09
    enburg
    0.09
    egger
    0.09
    éĩıçļĦ
    0.08
    enberg
    0.08
    ussin
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    ISED
    0.08
    arium
    0.08
    emberg
    0.08
    Activations Density 0.044%

    No Known Activations