© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8212
    Prev
    Next
    INDEX
    Explanations

    official bodies and appointments

    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
    ä¸įåıªæĺ¯
    -0.09
    åģ¥
    -0.08
    çĥŃ
    -0.08
    ç»ıèIJ¥
    -0.08
     Reform
    -0.08
     Burns
    -0.08
     vig
    -0.08
    grad
    -0.08
     lf
    -0.08
    åŀĤ
    -0.07
    POSITIVE LOGITS
    ä¸ĵ家
    0.14
    å°Ī家
    0.12
    ä¼ĹæīĢ
    0.12
     panel
    0.12
    æĻºåºĵ
    0.12
     Panel
    0.11
    ç§ī
    0.11
    éĿ¢æĿ¿
    0.11
    ä¸ĵ家ç»Ħ
    0.11
    panel
    0.10
    Activations Density 0.091%

    No Known Activations