© 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. 27210
    Prev
    Next
    INDEX
    Explanations

    deprotonation, phosphorylation

    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
    ike
    -0.06
    íķĺìħ¨
    -0.06
    ä¸ºæľŁ
    -0.06
    å¥Ĺ
    -0.06
    ople
    -0.06
    opl
    -0.06
    Decoder
    -0.06
    jet
    -0.06
    åīįåĪĹ
    -0.06
    lets
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.09
    atea
    0.08
    ouncer
    0.08
    ushman
    0.08
    ssp
    0.07
    为好
    0.07
    номо
    0.07
    å¾ĮçļĦ
    0.07
    kant
    0.07
    abad
    0.07
    Activations Density 0.001%

    No Known Activations