© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10408
    Prev
    Next
    INDEX
    Explanations

    achievement and impact

    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
    天æīį
    -0.09
    åĪ¶åĵģ
    -0.09
    ç«Ł
    -0.09
    elow
    -0.08
     Hel
    -0.08
    大éĿ¢ç§¯
    -0.08
    agina
    -0.08
    ãģĻãģĶãģĦ
    -0.08
    hel
    -0.08
    sworth
    -0.08
    POSITIVE LOGITS
    çĭ®
    0.12
    å¸ĮæľĽèĥ½
    0.11
    ç£ķ
    0.11
    å¿Ŀ
    0.10
    åĬĽæ±Ĥ
    0.10
    åĬĽäºī
    0.10
     hopefully
    0.10
    æĺ¯æĪijçļĦ
    0.10
    å¸ĮæľĽèĥ½å¤Ł
    0.10
    åħħå®ŀ
    0.09
    Activations Density 0.193%

    No Known Activations