© 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. 6470
    Prev
    Next
    INDEX
    Explanations

    founder and

    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
    çľ¼åīįçļĦ
    -0.11
    娣
    -0.09
    å¸ĸåŃIJ
    -0.09
    çľ¼åīį
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    çİ·
    -0.09
    Unnamed
    -0.09
    骥
    -0.09
    é«ĺ管
    -0.09
    è°¦
    -0.09
    POSITIVE LOGITS
    ulating
    0.09
    xis
    0.08
    ved
    0.08
    jom
    0.08
    æѤäºĭ
    0.08
    ä¹ĭä¸Ģ
    0.08
    æĭĦ
    0.08
    лÑij
    0.08
     Sanford
    0.08
    -env
    0.08
    Activations Density 0.115%

    No Known Activations