© 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. 42247
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns/articles

    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
    Äĥt
    -0.07
    æ®Ĭ
    -0.07
    hot
    -0.07
    vg
    -0.06
    ÅĤugi
    -0.06
    chio
    -0.06
    ifique
    -0.06
    ਼
    -0.06
    stitutions
    -0.06
    chin
    -0.06
    POSITIVE LOGITS
    ionales
    0.08
    ä¸ĸçļĦ
    0.08
    人æĿ¥è¯´
    0.08
    人æľī
    0.08
     sveta
    0.07
    åIJĮåѦéĥ½
    0.07
    &oacute
    0.07
    ÑĢÑıда
    0.07
    acers
    0.07
    ende
    0.07
    Activations Density 1.037%

    No Known Activations