© 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. 56892
    Prev
    Next
    INDEX
    Explanations

    on the edge/brink

    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
    建档
    -0.09
    appen
    -0.09
    纬
    -0.09
    ewise
    -0.09
    ãĤªãĥ¼
    -0.09
    太æŀģ
    -0.09
    æ¯Ĺ
    -0.09
    idy
    -0.09
    è°
    -0.08
    çķ¿
    -0.08
    POSITIVE LOGITS
     brink
    0.12
    è¾¹ç¼ĺ
    0.12
    æ¿Ĵ临
    0.11
     edge
    0.10
    éĿ¢ä¸´çĿĢ
    0.09
    说ä¸įåĩº
    0.09
    åĶĩ
    0.09
    çľ¼çľĭ
    0.09
    éĿ¢ä¸´
    0.09
    åĩłå¤©
    0.09
    Activations Density 0.054%

    No Known Activations