© 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. 50242
    Prev
    Next
    INDEX
    Explanations

    the word "to" when it appears as an infinitive marker or preposition in various contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     μÏĢο
    -0.08
    è¦ģ好好
    -0.08
    åħ·æľīä¸Ģå®ļçļĦ
    -0.08
     stripte
    -0.08
    èĥ½å¤ŁæĽ´å¥½åľ°
    -0.08
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    -0.08
    æĬ¥è®°èĢħ
    -0.08
    è®©æĽ´å¤ļçļĦ人
    -0.07
    强强
    -0.07
    好好çļĦ
    -0.07
    POSITIVE LOGITS
     micro
    0.08
     tiny
    0.07
    è¯Ħä»·ä½ĵç³»
    0.07
     curated
    0.07
    æѤåĪ»
    0.06
    å¾®åŀĭ
    0.06
     whispered
    0.06
    åıĻäºĭ
    0.06
    å¾®å°ı
    0.06
    N
    0.06
    Activations Density 0.000%

    No Known Activations