© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    manufacturing industry

    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
    åĨ¢
    -0.09
    çŃ¾åŃĹ
    -0.09
    æĮĸ
    -0.09
     CIA
    -0.09
    æŁ³
    -0.09
    åĬ¡å®ŀ
    -0.08
    çĥĪ
    -0.08
    ÑĤиÑĢов
    -0.08
    ä¸ĵåĪ©
    -0.08
    ç
    -0.08
    POSITIVE LOGITS
    ä¹ĭç¾İ
    0.10
    å¼ºåĽ½
    0.10
    å¤įåħ´
    0.08
    èĤĮ
    0.08
    åIJİèĢħ
    0.08
    åıĪ好
    0.08
    åħ³éŨ
    0.08
    éĩįå·¥
    0.08
    ä¸Ńæľī
    0.08
     пÑĢоÑĨ
    0.08
    Activations Density 0.026%

    No Known Activations