© 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. 57821
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by auxiliary or main verb

    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
    isco
    -0.08
    ÏģίÏĤ
    -0.08
    istr
    -0.08
    åľ¨è¿Ļä¸Ģ
    -0.08
    åįģä¸Ģç«ł
    -0.07
     ëĤĺìĦľ
    -0.07
    ivec
    -0.07
    åľ¨è¿Ļ
    -0.07
    为äºĨ满足
    -0.07
    éĴ§
    -0.07
    POSITIVE LOGITS
     respectively
    0.07
    ellet
    0.07
     indeed
    0.06
    onder
    0.06
    åį³åĪ°
    0.06
    ÄĻ
    0.06
    -même
    0.06
    жении
    0.06
    antino
    0.06
    flate
    0.06
    Activations Density 0.127%

    No Known Activations