© 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. 27214
    Prev
    Next
    INDEX
    Explanations

    words following punctuation or numbers

    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
    inand
    -0.08
    =nil
    -0.08
    atures
    -0.08
    vena
    -0.08
    วรรษ
    -0.08
    ÙĨب
    -0.07
    aimer
    -0.07
    andin
    -0.07
     Sej
    -0.07
    پر
    -0.07
    POSITIVE LOGITS
    iv
    0.07
    æt
    0.06
     Heights
    0.06
    ä¸ī代
    0.06
    iosi
    0.06
    wy
    0.06
    oloc
    0.06
    roof
    0.06
     Hor
    0.06
    æĽ´åħ·
    0.06
    Activations Density 0.005%

    No Known Activations