© 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. 16542
    Prev
    Next
    INDEX
    Explanations

    empty or null checks

    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
     convivencia
    -0.08
    erven
    -0.07
    apol
    -0.07
    àºĦ
    -0.07
    ÙĤت
    -0.07
     NotImplemented
    -0.07
    豪
    -0.07
    ubil
    -0.07
    åĬłå¾®ä¿¡
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    POSITIVE LOGITS
    空
    0.12
     empty
    0.12
    -empty
    0.12
    empty
    0.12
    (empty
    0.12
     empt
    0.12
    Empty
    0.11
    _empty
    0.11
     Empty
    0.11
    空èĻļ
    0.11
    Activations Density 0.076%

    No Known Activations