© 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. 56344
    Prev
    Next
    INDEX
    Explanations

    ionization and dissociation constants

    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
    éĽĨä¸Ń
    -0.07
    éĩįçĶ¨
    -0.07
     Sachs
    -0.07
    izu
    -0.07
     concent
    -0.07
    Hom
    -0.07
    çĴĢ
    -0.07
    stell
    -0.06
    hom
    -0.06
    å¼ĦèĻļä½ľåģĩ
    -0.06
    POSITIVE LOGITS
     acidic
    0.09
    ä¸ŃæĢ§
    0.09
     pH
    0.08
    两æĢ§
    0.08
    CIO
    0.08
     Asp
    0.08
    åŃ£
    0.08
    éħ¸çĶľ
    0.08
     Charg
    0.08
    éħ¸æĢ§
    0.08
    Activations Density 0.012%

    No Known Activations