© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59332
    Prev
    Next
    INDEX
    Explanations

    business requirements

    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
    Negative Logits
    çºłéĶĻ
    -0.09
    ourg
    -0.08
    igsaw
    -0.08
    ynth
    -0.08
    顶
    -0.08
    chooser
    -0.08
    æŀ¸
    -0.08
    èİ·å¾ĹæĽ´å¤ļ
    -0.08
    æĵİ
    -0.08
    thouse
    -0.08
    POSITIVE LOGITS
    éľĢæ±Ĥ
    0.16
    è¦ģæ±Ĥ
    0.12
    çļĦéľĢæ±Ĥ
    0.12
    客æĪ·éľĢæ±Ĥ
    0.11
     requirements
    0.10
    è¯īæ±Ĥ
    0.10
     ìļĶ구
    0.10
     needs
    0.10
     Requirements
    0.10
    å¸ĤåľºéľĢæ±Ĥ
    0.10
    Activations Density 0.129%

    No Known Activations