© 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. 49934
    Prev
    Next
    INDEX
    Explanations

    note followed by colon or description

    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
    ÙĨدر
    -0.09
    ness
    -0.09
    istrator
    -0.08
    /her
    -0.08
    sver
    -0.08
    доÑģÑĤа
    -0.08
    çī¹åĭĴ
    -0.08
    roads
    -0.08
    icke
    -0.08
    ibility
    -0.07
    POSITIVE LOGITS
    tingham
    0.10
    ungsweise
    0.09
    umbo
    0.09
    ìĤ¬íķŃ
    0.08
    withstanding
    0.08
     rằng
    0.08
    undial
    0.08
    vole
    0.08
     obstante
    0.08
    books
    0.07
    Activations Density 0.043%

    No Known Activations