© 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. 19962
    Prev
    Next
    INDEX
    Explanations

    latex code and chemical formulas

    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
    ier
    -0.08
    yr
    -0.08
    s
    -0.08
    iem
    -0.08
    ium
    -0.08
    iu
    -0.08
    ie
    -0.07
    ee
    -0.07
    si
    -0.07
    rot
    -0.07
    POSITIVE LOGITS
    Ĺı
    0.09
    åĬłæĭ¿å¤§
    0.09
    ../../../
    0.08
    俱ä¹IJéĥ¨
    0.08
    å°ĶçļĦ
    0.08
    AsStream
    0.08
    å·´å·´
    0.08
    ØŃØ©
    0.07
    å¤ļæľĪçļĦ
    0.07
    toor
    0.07
    Activations Density 0.053%

    No Known Activations