© 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. 40001
    Prev
    Next
    INDEX
    Explanations

    genetically modified or engineered

    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¡ĺ
    -0.10
    æĺ¯å¤ļä¹Ī
    -0.10
    丰åİļ
    -0.09
    åĨī
    -0.09
    é«ĺæ¡£
    -0.09
    ç¥ľ
    -0.09
    å¤ļä¹Ī
    -0.09
    .Fetch
    -0.08
    å¸ĮæľĽèĩªå·±
    -0.08
    arrant
    -0.08
    POSITIVE LOGITS
    ëIJľ
    0.09
    身躯
    0.09
    æİĸ
    0.08
    æĬĢæľ¯åĴĮ
    0.08
    @mail
    0.08
    dismiss
    0.08
    abb
    0.07
    Ùģض
    0.07
    ipt
    0.07
     %@
    0.07
    Activations Density 0.030%

    No Known Activations