© 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. 19982
    Prev
    Next
    INDEX
    Explanations

    time to

    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
    emiz
    -0.06
    æĺ¯åĽł
    -0.06
    æĺ¯åĽłä¸º
    -0.06
    rost
    -0.06
    tto
    -0.06
    åĽ°éļ¾
    -0.06
    èĵī
    -0.05
    åĽ½å¼º
    -0.05
    éģ¿åŃķ
    -0.05
    èĮ«
    -0.05
    POSITIVE LOGITS
    åĢ¾
    0.05
    oub
    0.05
    ä»Ĩ
    0.05
    صب
    0.05
     stuff
    0.05
    yled
    0.05
    å®ŀè·µèĥ½åĬĽ
    0.05
    åįĥçĻ¾
    0.05
    atical
    0.05
    ouse
    0.05
    Activations Density 0.032%

    No Known Activations