© 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. 22458
    Prev
    Next
    INDEX
    Explanations

    combined

    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
    ابت
    -0.05
    æĪĸå¤ļ
    -0.05
     wrought
    -0.05
    åıijåį¡
    -0.05
    驱
    -0.05
    ippy
    -0.05
    ëħIJ
    -0.05
    æł·çļĦ
    -0.05
    бÑĥ
    -0.05
    ç·Ĵ
    -0.05
    POSITIVE LOGITS
     Together
    0.11
     together
    0.11
     combined
    0.11
    Together
    0.10
    combined
    0.09
     zusammen
    0.08
     collectively
    0.08
     вмеÑģÑĤе
    0.08
     Combined
    0.08
     conjunto
    0.08
    Activations Density 0.094%

    No Known Activations