© 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. 43195
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by 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
    æľ¬æĸĩ为
    -0.07
    ï½ŀãĢĤ
    -0.07
    éĤ£æŶçļĦ
    -0.07
    s
    -0.07
    Ī
    -0.06
     ÑģÑĢазÑĥ
    -0.06
    éĺľ
    -0.06
    æѤæŶçļĦ
    -0.06
    thumb
    -0.06
    ī
    -0.05
    POSITIVE LOGITS
    urin
    0.08
    ulfilled
    0.08
    :max
    0.08
    ×ķש
    0.08
    ÙĪÙħت
    0.08
    uzu
    0.08
    =pk
    0.08
    uesa
    0.08
    owering
    0.08
    é¡»çŁ¥
    0.08
    Activations Density 0.027%

    No Known Activations