© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    an followed by a vowel sound

    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
    ìķ¼
    -0.09
    ffect
    -0.08
    боÑĤ
    -0.08
    Ìģ
    -0.08
    Ùĭ
    -0.08
    а
    -0.08
    를
    -0.07
    ffects
    -0.07
    ÑģÑĮ
    -0.07
    less
    -0.07
    POSITIVE LOGITS
    à¸Ļิ
    0.11
    à¸Ļาà¸Ļ
    0.11
    à¸Ļัà¹īà¸Ļ
    0.11
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.10
    rise
    0.10
    à¸Ļัà¸ļ
    0.10
    lah
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.10
    åijIJ
    0.10
    à¸Ļà¸Ńà¸ģ
    0.10
    Activations Density 0.329%

    No Known Activations