© 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. 50147
    Prev
    Next
    INDEX
    Explanations

    links, lists, or dataframes

    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
    .TestCase
    -0.08
    jna
    -0.08
    coa
    -0.08
    ajara
    -0.08
    achinery
    -0.07
    ongan
    -0.07
    deaux
    -0.07
    agini
    -0.07
    mey
    -0.07
    ication
    -0.07
    POSITIVE LOGITS
    ielo
    0.07
    ioni
    0.07
    ork
    0.07
    iel
    0.07
     nho
    0.07
    orte
    0.06
    orem
    0.06
    зоÑĢ
    0.06
    asso
    0.06
    rch
    0.06
    Activations Density 0.058%

    No Known Activations