© 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. 63995
    Prev
    Next
    INDEX
    Explanations

    blood pH measurements

    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
    æĪijä¹Łåİ»
    -0.09
    æŃ¤èµ·å½¼
    -0.09
    pliers
    -0.08
    gan
    -0.08
     mastur
    -0.08
     intestin
    -0.08
    åı£åijĨ
    -0.08
    itari
    -0.08
    åĽŀé¦ĸ
    -0.08
    گاÙĨ
    -0.08
    POSITIVE LOGITS
     pH
    0.09
     acid
    0.08
    leans
    0.07
    éħ¸
    0.07
    éħ¸ç¢±
    0.07
     deficit
    0.07
     respiratory
    0.07
    ä¸īçĶ²
    0.07
    0.07
     equilibr
    0.06
    Activations Density 0.037%

    No Known Activations