© 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. 19219
    Prev
    Next
    INDEX
    Explanations

    in order

    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
    åĪ°ä½į
    -0.12
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
     Sav
    -0.08
    lot
    -0.08
    å¾Ĺèµ·
    -0.08
    æĸ°å±ĢéĿ¢
    -0.08
    лаÑĤ
    -0.08
    åģ¥åħ¨
    -0.08
    ilot
    -0.08
    -wise
    -0.08
    POSITIVE LOGITS
    å¸ĮæľĽèĥ½å¤Ł
    0.13
    æĺ¯ä¸ºäºĨ
    0.12
    以便
    0.12
     ÑĩÑĤобÑĭ
    0.12
    å¸ĮæľĽéĢļè¿ĩ
    0.12
    为äºĨ让
    0.12
    缮çļĦæĺ¯
    0.11
    å¸ĮæľĽèĥ½
    0.11
    为äºĨ
    0.10
    å°±æĺ¯ä¸ºäºĨ
    0.10
    Activations Density 0.241%

    No Known Activations