© 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. 11516
    Prev
    Next
    INDEX
    Explanations

    infection, risk, complications

    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
    åĬ©äºİ
    -0.08
    cade
    -0.07
    geführ
    -0.07
     Ñģно
    -0.07
    oted
    -0.07
    posts
    -0.07
    otal
    -0.07
    ä¸įå¹³
    -0.07
    _FAULT
    -0.06
    .Failure
    -0.06
    POSITIVE LOGITS
    çļĦåı¯èĥ½æĢ§
    0.11
    åı¯èĥ½æĢ§
    0.10
    é£İéĻ©
    0.09
    çļĦé£İéĻ©
    0.09
     risk
    0.08
    æľªçĦ¶
    0.08
    é£İéĻ©çļĦ
    0.08
    é£İéĻ©åĴĮ
    0.08
    åĩłçİĩ
    0.08
    é«ĺåıij
    0.08
    Activations Density 0.169%

    No Known Activations