© 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. 22543
    Prev
    Next
    INDEX
    Explanations

    names followed by birth year

    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
    Negative Logits
    usso
    -0.07
    جاÙħ
    -0.06
     mor
    -0.06
    天çĦ¶
    -0.05
    ement
    -0.05
     à¸ĸ
    -0.05
    resse
    -0.05
    ual
    -0.05
    æŁĵ
    -0.05
    staking
    -0.05
    POSITIVE LOGITS
    énk
    0.06
    лак
    0.06
    janya
    0.06
    ynos
    0.06
    ä»ĸ对
    0.06
    engi
    0.05
    æĻĮ
    0.05
     Destin
    0.05
    ä¸Ģ个æĸ°
    0.05
     habló
    0.05
    Activations Density 0.146%

    No Known Activations