© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22358
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    ?v
    -0.06
    hein
    -0.06
    owali
    -0.06
    makta
    -0.06
    帥
    -0.06
     Tune
    -0.06
    ä½Ĩæĺ¯ä»ĸ们
    -0.06
    个æĪĸå¤ļ个
    -0.06
    ught
    -0.06
    彦
    -0.06
    POSITIVE LOGITS
     Harr
    0.06
    ighted
    0.06
    ÙĪÙĦÙĬØ©
    0.05
    ista
    0.05
    ible
    0.05
    ä¸Ĭå¸ĤåIJİ
    0.05
    edo
    0.05
     sortes
    0.05
    çĤ
    0.05
     justa
    0.05
    Activations Density 0.013%

    No Known Activations