© 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. 26997
    Prev
    Next
    INDEX
    Explanations

    gene encodes protein

    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
    æĿ¿åĿĹ
    -0.09
    æŃ»
    -0.08
     plates
    -0.08
     plate
    -0.08
     entr
    -0.08
    rote
    -0.08
     Ye
    -0.08
    Ye
    -0.08
    éĢĢ
    -0.08
    RO
    -0.08
    POSITIVE LOGITS
    ä¹ī
    0.10
    产åĢ¼
    0.10
     SSP
    0.09
    ÇIJ
    0.09
    åĮĸ身
    0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.09
    修补
    0.09
    ç²¾éĢļ
    0.09
    éĻ¢åŃIJéĩĮ
    0.09
    è¿ĺ好
    0.09
    Activations Density 0.353%

    No Known Activations