© 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. 40523
    Prev
    Next
    INDEX
    Explanations

    monovalent and divalent ions

    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
    ombe
    -0.08
    ekan
    -0.08
    eken
    -0.08
    å°±æĺ¯æľĢ好çļĦ
    -0.07
     seper
    -0.07
    ìĤ
    -0.07
    bürger
    -0.07
    è¿ĩç¥ŀ
    -0.07
    åķ¡
    -0.07
    resso
    -0.07
    POSITIVE LOGITS
    /single
    0.10
     single
    0.09
    åĬłåĢį
    0.08
    åįķ
    0.08
    ä¸īåĢį
    0.08
     اÙĦÙĪاØŃد
    0.08
    (single
    0.07
    _requires
    0.07
    为éĩį
    0.07
    single
    0.07
    Activations Density 0.026%

    No Known Activations