© 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. 37339
    Prev
    Next
    INDEX
    Explanations

    nearing or on the edge

    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
    é»ijçĻ½
    -0.09
     sting
    -0.09
     Inn
    -0.08
    åŃ£
    -0.08
    ÑĤиÑĢ
    -0.08
    victim
    -0.08
    mirror
    -0.08
     dreamed
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
     Morse
    -0.08
    POSITIVE LOGITS
     Dangerous
    0.10
    ãģ¤ãģį
    0.10
    好åĥıæĺ¯
    0.09
    幸è¿IJ
    0.09
    çĥŁçģ«
    0.09
    åIJ¬å¾Ĺ
    0.09
    æľīæŶåĢĻ
    0.09
    åį±éĻ©
    0.09
    ASS
    0.09
    åı¯ä»¥è¯´æĺ¯
    0.09
    Activations Density 0.018%

    No Known Activations