© 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. 63071
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by location or direction

    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
    atkan
    -0.08
    è°·
    -0.07
    æľ¬æĸĩçĶ±
    -0.07
    رÛĮÙģ
    -0.07
    connexion
    -0.06
    arkan
    -0.06
    å·²èµŀè¿ĩ
    -0.06
    irman
    -0.06
    æĪij们çļĦ产åĵģ
    -0.06
    AndGet
    -0.06
    POSITIVE LOGITS
     thereof
    0.17
     daarvan
    0.13
     ervan
    0.11
    ãģĿãĤĮãģ«
    0.11
    éļıä¹ĭ
    0.11
     hierv
    0.10
     dalamnya
    0.10
     therein
    0.10
    çĶ±æѤ
    0.10
     them
    0.10
    Activations Density 0.448%

    No Known Activations