© 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. 23726
    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
    ä¹Łæĺ¯æľĢ
    -0.06
    iller
    -0.06
    isson
    -0.06
    ä¸Ģè¨Ģ
    -0.06
    ogue
    -0.06
    åĴĮ责任
    -0.06
    esson
    -0.06
    áĢ²
    -0.06
    çļĦåĸľæĤ¦
    -0.06
    еÑģÑĮ
    -0.06
    POSITIVE LOGITS
    oud
    0.08
    åħ¶èĩªçĦ¶
    0.07
    à¹Ĩ
    0.07
    inë
    0.07
    éĢĤå½ĵçļĦ
    0.07
     (~(
    0.07
    olge
    0.07
    åħ¶
    0.07
    ä¹ĭ为
    0.07
    มà¸ģลาà¸ĩ
    0.07
    Activations Density 1.018%

    No Known Activations