© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    èĹīæѤ
    -0.06
    .ordinal
    -0.06
    orous
    -0.06
     com
    -0.06
    æĭĮ
    -0.06
    èĽ®
    -0.06
     Lotto
    -0.06
    ag
    -0.06
    y
    -0.06
    stuff
    -0.06
    POSITIVE LOGITS
    ék
    0.08
    ëŀĺ
    0.08
    веÑģÑĤ
    0.08
    беÑĢ
    0.08
    大ä¸Ńåŀĭ
    0.08
    ç»´åŁºçĻ¾ç§ij
    0.08
    ictured
    0.08
    eldon
    0.08
    æĶ¶äºİ
    0.08
    asured
    0.08
    Activations Density 0.033%

    No Known Activations