© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19676
    Prev
    Next
    INDEX
    Explanations

    mortal physical form

    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
    åıįä¹ĭ
    -0.09
    çĶŁäº§åİĤ家
    -0.09
    oned
    -0.09
    ä¸Ģçķª
    -0.09
    æĥŃ
    -0.09
    éķ³
    -0.09
    æĢª
    -0.09
    èĿĹ
    -0.09
    ĥģ
    -0.09
    æĭ§
    -0.09
    POSITIVE LOGITS
    身躯
    0.11
    æĻ®éĢļ
    0.10
    æĻ®éĢļ人
    0.10
     Flesh
    0.10
     ENC
    0.10
    人éĹ´
    0.09
    ä¸ĸä¿Ĺ
    0.09
    inary
    0.08
    寻常
    0.08
    寰
    0.08
    Activations Density 0.058%

    No Known Activations