© 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. 4270
    Prev
    Next
    INDEX
    Explanations

    medical conditions compared

    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
    igrations
    -0.07
     saving
    -0.07
    å¾·ç½Ĺ
    -0.06
     simultaneous
    -0.06
    ähr
    -0.06
    åİŁæĺ¯
    -0.06
    æĦŁæģ©èĬĤ
    -0.06
    hui
    -0.06
    dak
    -0.06
    ä¸Ģ鸣
    -0.06
    POSITIVE LOGITS
    _vs
    0.09
     vs
    0.08
     compared
    0.08
    -vs
    0.08
     Compared
    0.08
    åĴĮå¹³
    0.08
    æł·æľ¬
    0.07
     versus
    0.07
    vs
    0.07
     samples
    0.07
    Activations Density 1.606%

    No Known Activations