© 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. 30457
    Prev
    Next
    INDEX
    Explanations

    tube or tubes

    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
    antic
    -0.08
    pard
    -0.08
    s
    -0.07
    ģ
    -0.07
    maal
    -0.07
    scape
    -0.07
    主æĦı
    -0.07
    ²
    -0.07
    wert
    -0.07
    ithe
    -0.07
    POSITIVE LOGITS
    åĨħçļĦ
    0.11
    ÑĩаÑĤ
    0.09
    zinho
    0.09
    lets
    0.09
    ajor
    0.08
    ëij¥
    0.08
    INESS
    0.08
    ULAR
    0.08
    omial
    0.08
    ercul
    0.08
    Activations Density 0.044%

    No Known Activations