© 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. 56894
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
    æĪ¿éĹ´éĩĮ
    -0.09
    éĻĭ
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.08
    寡
    -0.08
    art
    -0.08
    è¦ģä¹Ī
    -0.08
    éĢ¼è¿ij
    -0.08
    unar
    -0.08
    erm
    -0.08
    xd
    -0.07
    POSITIVE LOGITS
    çıį
    0.11
    é¢IJ
    0.09
    æĶ¿çŃĸæݪæĸ½
    0.09
    æŃ£å¼ıåIJ¯åĬ¨
    0.09
     Ùħباشرة
    0.09
    人åĬĽ
    0.09
    itals
    0.09
    大éģĵ
    0.09
    eline
    0.09
    halb
    0.09
    Activations Density 0.073%

    No Known Activations