© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42554
    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
    èµ·ä½ľçĶ¨
    -0.08
    å·¥ä½ľå¼Ģå±ķ
    -0.08
    æ·ij
    -0.08
     nodig
    -0.07
    iola
    -0.07
    æĿ¥èĩªä¸ŃåĽ½
    -0.07
    ux
    -0.07
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.07
    .vars
    -0.07
    ðŁĺī
    -0.07
    POSITIVE LOGITS
     with
    0.09
     without
    0.08
     on
    0.08
     in
    0.08
     dengan
    0.08
     at
    0.07
     dalam
    0.07
     differently
    0.07
     иÑģклÑİÑĩиÑĤелÑĮно
    0.07
    /write
    0.07
    Activations Density 0.666%

    No Known Activations