© 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. 15189
    Prev
    Next
    INDEX
    Explanations

    pH and acidity

    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
    åĬłåĢį
    -0.08
    oci
    -0.07
    à¤Ĺत
    -0.07
    oxel
    -0.07
     Satellite
    -0.07
     Stamm
    -0.07
    otte
    -0.07
     spokes
    -0.07
     satellites
    -0.07
    ä¿Ŀ温æĿIJæĸĻ
    -0.06
    POSITIVE LOGITS
     pH
    0.16
    éħ¸ç¢±
    0.15
     acidic
    0.14
     acidity
    0.13
    éħ¸æĢ§
    0.12
    éħ¸
    0.12
     acid
    0.11
    acid
    0.11
     Acid
    0.11
    éħ¸åĮĸ
    0.10
    Activations Density 0.085%

    No Known Activations