© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21841
    Prev
    Next
    INDEX
    Explanations

    cytochromes and thioredoxins

    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
    æłĭæ¢ģ
    -0.07
     trek
    -0.07
    awa
    -0.07
    ä¸įå°½
    -0.06
    ents
    -0.06
     ál
    -0.06
     Slate
    -0.06
    符
    -0.06
    å°Ĩ士
    -0.06
    夫æĸ¯åŁº
    -0.06
    POSITIVE LOGITS
    æ¯
    0.07
    ä½ĩ
    0.07
    Å¡el
    0.07
    pod
    0.07
    achable
    0.07
    irro
    0.07
    queue
    0.07
    istel
    0.06
    -po
    0.06
    irros
    0.06
    Activations Density 0.095%

    No Known Activations