© 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. 32851
    Prev
    Next
    INDEX
    Explanations

    past tense 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
    æ±IJ
    -0.07
    ceau
    -0.07
    powers
    -0.07
    .fromString
    -0.07
    æ°ĶäºĨ
    -0.07
     pParent
    -0.06
    æ°ĶåĴĮ
    -0.06
    çIJĨçļĦ
    -0.06
    .credentials
    -0.06
    rowsable
    -0.06
    POSITIVE LOGITS
    人æĪĸ
    0.08
     Weinstein
    0.07
    æĪĸå¤ļ个
    0.07
    +N
    0.07
    /npm
    0.06
    åĬ¨è¯į
    0.06
    å¥Īä½ķ
    0.06
    åı¥å¼ı
    0.06
    éĥ½æĺ¯æ¯Ķè¾ĥ
    0.06
    表示èĩªå·±
    0.06
    Activations Density 0.005%

    No Known Activations