© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19349
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bito
    -0.08
     ê°ĢëĬ¥íķĺë©°
    -0.06
     Rupert
    -0.06
    cce
    -0.05
    ãĥ©ãĤ°
    -0.05
    :...
    -0.05
    amá
    -0.05
     gaping
    -0.05
    Ø´ÙĬ
    -0.05
    äºĪå®ļãģ§ãģĻ
    -0.05
    POSITIVE LOGITS
     conduct
    0.06
    ordia
    0.06
     scarce
    0.06
    ä¸įåı¯æĪĸ缺çļĦ
    0.05
    pron
    0.05
    åľ¨æ²¡æľī
    0.05
    æĺ¯è°ģ
    0.05
    æĥľ
    0.05
     continu
    0.05
    raud
    0.05
    Activations Density 0.034%

    No Known Activations