© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    pH, acidity, and neutrality

    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
    ragment
    -0.08
    ceaux
    -0.08
    cross
    -0.08
    linger
    -0.08
    intree
    -0.08
    ework
    -0.08
    -cross
    -0.08
    scatter
    -0.08
    çŃĭèĨľ
    -0.08
    -ignore
    -0.08
    POSITIVE LOGITS
     pH
    0.16
     neutral
    0.12
     acidic
    0.12
    ä¸ŃåĴĮ
    0.11
     neutrality
    0.11
     acidity
    0.11
    éħ¸ç¢±
    0.11
     Neutral
    0.10
    neutral
    0.10
    Neutral
    0.10
    Activations Density 0.012%

    No Known Activations