© 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. 9989
    Prev
    Next
    INDEX
    Explanations

    modal verbs modifying subject

    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
    ä½łæĬĬ
    -0.09
    æĸ¹å¼ı使çĶ¨
    -0.09
    ä½łçĶ¨
    -0.08
    åĽłç´łå½±åĵį
    -0.08
    ä»ĸæĬĬ
    -0.08
     conseguimos
    -0.08
    ä»ĸçĶ¨
    -0.08
    æľĪåľ¨
    -0.08
    æĪij们æĬĬ
    -0.07
    æĪij们çĶ¨
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½ä¼ļ
    0.19
     might
    0.18
    åı¯èĥ½ä¼ļæľī
    0.17
     may
    0.17
    åı¯èĥ½æľĥ
    0.16
     could
    0.16
    åı¯èĥ½ä¼ļ被
    0.16
    ä¹Łè®¸ä¼ļ
    0.15
    åı¯èĥ½ä¼ļåĩºçİ°
    0.15
     potrebbe
    0.15
    Activations Density 0.734%

    No Known Activations