© 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. 6949
    Prev
    Next
    INDEX
    Explanations

    with a

    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
    Anywhere
    -0.10
    usk
    -0.09
    å§ĭ
    -0.09
    ç³Ļ
    -0.09
    å®Ī
    -0.09
    èµ°è¿ij
    -0.09
    è°Ĺ
    -0.08
    æŃ£åĵģ
    -0.08
    éľı
    -0.08
    éĥ½ä¼ļæľī
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.10
    жа
    0.09
     no
    0.09
    大éĥ¨åĪĨ
    0.08
    缮æłĩ
    0.08
    ç»Ģ
    0.08
    åĩ¹
    0.08
     вÑģÑij
    0.08
    æĢ¥éľĢ
    0.08
    å¸Ĥåľºä»·æł¼
    0.08
    Activations Density 0.044%

    No Known Activations