© 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. 62404
    Prev
    Next
    INDEX
    Explanations

    lipophilic, lipid, solvent, partition coefficients

    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
    åį«
    -0.08
    forc
    -0.08
    agrid
    -0.07
     runt
    -0.07
    æĹ©æĻļ
    -0.07
    ucar
    -0.07
     sob
    -0.07
    æĥ©
    -0.07
    awk
    -0.07
     humility
    -0.07
    POSITIVE LOGITS
     oily
    0.09
     oil
    0.09
     lipid
    0.08
    oil
    0.08
     oils
    0.08
    æ²¹èĦĤ
    0.08
    æ£ķæ¦Ī
    0.07
     Oil
    0.07
    æ²¹çļĦ
    0.07
    andle
    0.07
    Activations Density 0.042%

    No Known Activations