© 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. 60816
    Prev
    Next
    INDEX
    Explanations

    pH values

    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
    Įĵ
    -0.08
    æ¡ĪçļĦ
    -0.07
    -contrib
    -0.07
    ãi
    -0.07
    lineno
    -0.07
    豪
    -0.07
     Inizi
    -0.07
    hein
    -0.07
    ildo
    -0.07
    èį·å°ĶèĴĻ
    -0.07
    POSITIVE LOGITS
     neutral
    0.09
    ä¸ŃæĢ§
    0.09
    neutral
    0.08
     Neutral
    0.07
     pH
    0.07
     neutrality
    0.07
     Duffy
    0.07
    Neutral
    0.07
    ä¸ŃåĴĮ
    0.06
    游离
    0.06
    Activations Density 0.016%

    No Known Activations