© 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. 34602
    Prev
    Next
    INDEX
    Explanations

    create and modify components

    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
    éĽĦåİļ
    -0.10
    人人éĥ½
    -0.09
    ãģĵãģĿ
    -0.09
    人人
    -0.08
    è¿Ļéĥ¨
    -0.08
     dra
    -0.08
    ä¸ĵå¿ĥ
    -0.08
    Merit
    -0.08
    nj
    -0.08
    æ·±åĪĩ
    -0.08
    POSITIVE LOGITS
    ÂŃs
    0.11
    åĩºå±Ģ
    0.09
    è°ª
    0.09
    为åĩĨ
    0.09
    æ²Ľ
    0.09
    ç¾ļ
    0.08
    æIJ¦
    0.08
    ç²¹
    0.08
    é«ĺç§ijæĬĢ
    0.08
    ä¸Ģè§Ī
    0.08
    Activations Density 0.120%

    No Known Activations