© 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. 33366
    Prev
    Next
    INDEX
    Explanations

    -ly suffix verbs

    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
    èĢĮèĩªå·±
    -0.08
    ¤íĹ
    -0.07
    cego
    -0.07
    GRESS
    -0.07
    elmet
    -0.07
    ç§ijåѦä¸İæĬĢæľ¯
    -0.07
    èles
    -0.07
    ãĥ¤ãĥ¼
    -0.07
    presas
    -0.07
    érieures
    -0.07
    POSITIVE LOGITS
    ablish
    0.11
    istically
    0.10
    ingly
    0.09
    lessly
    0.09
    èĮĥæĸĩç½ij
    0.09
    æĶ¾çŁ¢
    0.08
    åIJįæĢĿ
    0.07
    æĨ¬
    0.07
    ously
    0.07
    æľ¨æĸ¯
    0.07
    Activations Density 8.687%

    No Known Activations