© 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. 34630
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    驾
    -0.09
    leman
    -0.08
    ạch
    -0.08
    and
    -0.07
    hof
    -0.07
    夺
    -0.07
    åĨįä¸į
    -0.07
    ioni
    -0.07
    æĸ½
    -0.07
    (expected
    -0.07
    POSITIVE LOGITS
    ivit
    0.07
    ä¸Ģå¤ķ
    0.06
    ä¸įçŁ¥éģĵçļĦ
    0.06
     placement
    0.06
    tm
    0.06
    ãĥĥãĤ¿
    0.06
    ?,?,
    0.06
    ä¸Ģæĸ°
    0.06
    tis
    0.06
    pps
    0.06
    Activations Density 0.007%

    No Known Activations