© 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. 40973
    Prev
    Next
    INDEX
    Explanations

    angiotensin cascade

    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
    课å¤ĸ
    -0.07
    è·Ŀ
    -0.07
     Wig
    -0.07
    éģ¥éģ¥
    -0.07
    .attrib
    -0.06
    å¯Ŀ
    -0.06
    åĤ»äºĨ
    -0.06
    è¹Ī
    -0.06
    eger
    -0.06
    кла
    -0.06
    POSITIVE LOGITS
     cascade
    0.08
    dyn
    0.08
     Contracts
    0.08
     Favor
    0.08
    åĪ©å°¿
    0.08
    èĤ¾åĬŁèĥ½
    0.08
    avored
    0.07
     ÙĦصاÙĦØŃ
    0.07
     doux
    0.07
    cascade
    0.07
    Activations Density 0.038%

    No Known Activations