© 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. 46904
    Prev
    Next
    INDEX
    Explanations

    Ð and Russian words

    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
    ful
    -0.09
    ï¸ı
    -0.08
    avery
    -0.08
    ing
    -0.07
    inkle
    -0.07
    å¾Īå¿Ļ
    -0.07
    ish
    -0.07
    à¦ĩ
    -0.07
    缨
    -0.07
    没æľīåľ¨
    -0.07
    POSITIVE LOGITS
    uten
    0.09
    à¸ķัว
    0.08
    žo
    0.07
    ute
    0.07
    tern
    0.07
    ÑĤом
    0.07
    å¾Ĺå¿ĥ
    0.07
    aten
    0.07
    ä¹ĭåıĪ
    0.07
    utes
    0.07
    Activations Density 0.009%

    No Known Activations