© 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. 16453
    Prev
    Next
    INDEX
    Explanations

    etiology of diseases

    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
    èĤ¤
    -0.07
    æĮº
    -0.07
    å«
    -0.07
    opot
    -0.07
    leter
    -0.07
    天å°Ĭ
    -0.07
    SQLite
    -0.06
    aday
    -0.06
    便åĪ©
    -0.06
     incid
    -0.06
    POSITIVE LOGITS
     underlying
    0.09
    è§ģäºİ
    0.09
    æīĢèĩ´
    0.09
    è¿ijæľŁ
    0.09
     causes
    0.08
    æĬijæĪĸ
    0.08
    AIN
    0.08
     impending
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
    çŃīåİŁåĽł
    0.08
    Activations Density 0.265%

    No Known Activations