© 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. 58073
    Prev
    Next
    INDEX
    Explanations

    Echinococcus, vitrectomy, composite, cyclo, Schistosoma, heart

    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
    ed
    -0.07
     ({
    -0.06
    EO
    -0.06
    %%%
    -0.06
     decade
    -0.06
    ä¹ĭæģĭ
    -0.06
    اÙĪر
    -0.06
    lide
    -0.06
     (~
    -0.06
    arella
    -0.06
    POSITIVE LOGITS
    ocity
    0.08
     تÙĩ
    0.08
    åħ¬åı¸æĪIJåijĺ
    0.08
    agak
    0.08
     обÑĬ
    0.08
    ént
    0.08
    æĸĽ
    0.08
    管çIJĨåѦ
    0.07
    TypeDef
    0.07
    łĢ
    0.07
    Activations Density 0.001%

    No Known Activations