© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17801
    Prev
    Next
    INDEX
    Explanations

    virus genome replication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    å¸Ĥåľºä»·æł¼
    -0.10
    اÙĪÙĬ
    -0.09
     Pole
    -0.09
    å¸Ĥåľºè§Ħ模
    -0.09
    Violation
    -0.09
     Deg
    -0.08
    pee
    -0.08
     деÑĢ
    -0.08
    adium
    -0.08
    Deg
    -0.08
    POSITIVE LOGITS
    æĹħ客
    0.10
    横åIJij
    0.09
    ç§ij
    0.09
    èµĽåIJİ
    0.09
    éĢ»
    0.09
     Hind
    0.09
    åĢŁ
    0.09
    éģ¿åŃķ
    0.09
     sik
    0.08
    祯
    0.08
    Activations Density 0.301%

    No Known Activations