© 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. 18700
    Prev
    Next
    INDEX
    Explanations

    ethnic, religious, and social groups

    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
    z
    -0.07
    èĢIJ
    -0.05
     bulk
    -0.05
    ch
    -0.05
    K
    -0.05
     Bulk
    -0.05
     say
    -0.05
    çłĶ究ä¸İ
    -0.05
     coding
    -0.05
    bulk
    -0.05
    POSITIVE LOGITS
    нÑij
    0.07
    abouts
    0.06
    hj
    0.06
    ียà¸ĩ
    0.06
    bürger
    0.06
    è¿ĩåĪĨ
    0.06
    partis
    0.06
    è¿ĩ度çļĦ
    0.06
    ãģıãģłãģķãģ£ãģŁ
    0.06
    étaient
    0.06
    Activations Density 0.009%

    No Known Activations