© 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. 48799
    Prev
    Next
    INDEX
    Explanations

    flavenoids and medicinal compounds

    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
    éĩij马
    -0.09
    ipel
    -0.08
    erschaft
    -0.08
    reste
    -0.08
    ohner
    -0.07
    ointed
    -0.07
    é¼İ
    -0.07
    æīĢ欲
    -0.07
    CanBe
    -0.07
    iali
    -0.07
    POSITIVE LOGITS
    isor
    0.07
    noop
    0.06
    ä¸Ģç§į
    0.06
     ubiqu
    0.06
    ability
    0.06
    ãĥ¶
    0.06
    agon
    0.06
    itone
    0.06
    æľ¬çº§
    0.06
    an
    0.06
    Activations Density 0.286%

    No Known Activations