© 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. 50045
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    åįĬéĢĶ
    -0.07
    ä¸ŃéĢĶ
    -0.07
    à§įষ
    -0.07
    çĽĪçĽĪ
    -0.07
    ooter
    -0.07
     ÙĪاÙĦÙħÙĦ
    -0.07
    ocas
    -0.07
    Ĭ
    -0.07
    äj
    -0.07
    tails
    -0.07
    POSITIVE LOGITS
     numerous
    0.13
    çļĦä¸ĢäºĽ
    0.12
    éĥ½æĺ¯ä¸ĢäºĽ
    0.11
    å¯ĨéĽĨ
    0.11
    ä¸Ģç³»åĪĹ
    0.11
    äºĨä¸Ģç³»åĪĹ
    0.11
    çļĦä¸Ģç³»åĪĹ
    0.10
    ä¸Ģ个ä¸Ģ个
    0.10
    ãģĦãģıãģ¤ãģĭ
    0.10
    åĵªäºĽ
    0.10
    Activations Density 1.665%

    No Known Activations