© 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. 32295
    Prev
    Next
    INDEX
    Explanations

    blood pressure regulation

    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
     probabil
    -0.08
    iterated
    -0.07
     separ
    -0.07
     deteri
    -0.07
    зиÑĤ
    -0.07
     annihil
    -0.07
    itan
    -0.06
     holog
    -0.06
    dna
    -0.06
     infinit
    -0.06
    POSITIVE LOGITS
    ä¸Ńæŀ¢
    0.09
    overrides
    0.09
     increased
    0.08
    åĬ¨åijĺ
    0.08
     decreased
    0.08
     redistribution
    0.08
     paradox
    0.08
    æĤ£èĢħåľ¨
    0.08
    è¿ħéĢŁ
    0.08
    patient
    0.08
    Activations Density 0.160%

    No Known Activations