© 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. 38635
    Prev
    Next
    INDEX
    Explanations

    knowledge and understanding regarding

    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
    ä½łä¸į
    -0.09
    è¾ĥ大çļĦ
    -0.09
    ä½łè§īå¾Ĺ
    -0.09
    ä¸ĢçĶŁ
    -0.09
    ä½łä¹Ł
    -0.08
    åħ±åIJĮ
    -0.08
     suger
    -0.08
    æIJºå¸¦
    -0.08
    ulatory
    -0.08
    çľĭä¸įåĩº
    -0.08
    POSITIVE LOGITS
    åĬłå¼ºå¯¹
    0.11
    认è¯Ĩ
    0.10
    æĮ¹
    0.09
    çIJ¶
    0.09
    éĻį
    0.09
    çļĩåŃIJ
    0.09
    éĵĻ
    0.09
    å¾Īå¤ļ
    0.09
    çĹħåĽł
    0.09
    anged
    0.09
    Activations Density 0.267%

    No Known Activations