© 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. 48378
    Prev
    Next
    INDEX
    Explanations

    you asking/thinking/doing

    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
    å½±åĵįåĬĽçļĦ
    -0.10
    folio
    -0.09
    urch
    -0.09
    ä¹ŁéĿŀ常
    -0.09
    ä¹Łå¾Ī
    -0.09
    åºĵéĩĮ
    -0.09
    quire
    -0.09
    ä¸Ģå¦Ĥ
    -0.09
    .CG
    -0.08
    æĻĸ
    -0.08
    POSITIVE LOGITS
    chia
    0.09
    æĹĮ
    0.09
    инг
    0.09
    éĤ£ä¹Īå¤ļ
    0.09
    æĢĿãģĦãģ¾ãģĻ
    0.09
    注å®ļ
    0.08
     czÄĻÅĽci
    0.08
    æĹĥ
    0.08
    aldo
    0.08
    sst
    0.08
    Activations Density 0.029%

    No Known Activations