© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
    好åĩłä¸ª
    -0.08
    åĩłå®¶
    -0.08
    anche
    -0.07
    sic
    -0.07
    licated
    -0.07
    ILA
    -0.07
    以ä¸ĭåĩłä¸ª
    -0.07
    许å¤ļçļĦ
    -0.07
     Noble
    -0.07
    å·¥ä½ľä»»åĬ¡
    -0.06
    POSITIVE LOGITS
    izzo
    0.08
     behalf
    0.08
    /respond
    0.07
     поводÑĥ
    0.07
    gue
    0.07
    æīĢå±ŀåĪĨç±»
    0.07
    annen
    0.07
    áv
    0.07
    /about
    0.07
    ieten
    0.06
    Activations Density 0.368%

    No Known Activations