© 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. 32122
    Prev
    Next
    INDEX
    Explanations

    philosophy and philosophical

    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
    ä¹ĭ声
    -0.10
    ãĤĪãģĨãģª
    -0.09
    æĥħåĨµ
    -0.08
    é£İéĩĩ
    -0.08
    achi
    -0.08
     prime
    -0.08
    ish
    -0.08
    两åij¨
    -0.08
    è¿Ļ个è¡Įä¸ļ
    -0.08
    adow
    -0.07
    POSITIVE LOGITS
    åĬŁ
    0.11
    åĵ²åѦ
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
    çĻ¾å®¶
    0.09
    满满
    0.09
    åĶij
    0.09
    ä¹ĭæĪĺ
    0.09
    oucher
    0.09
    çĬ¯ç½ªå«Įçĸij
    0.09
    ç²¾çĽĬ
    0.09
    Activations Density 0.022%

    No Known Activations