© 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. 49187
    Prev
    Next
    INDEX
    Explanations

    life is

    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
    çľ¼ä¸Ń
    -0.09
    çĶŁæ´»çݯå¢ĥ
    -0.09
    åİī害
    -0.08
    ige
    -0.08
    家éĩĮ
    -0.08
    çľ¼éĩĮ
    -0.08
    åħĪè¡Į
    -0.08
    å´¿
    -0.08
    éķĮ
    -0.08
    ä½ĵè´¨
    -0.08
    POSITIVE LOGITS
    èĤ¡
    0.09
    tré
    0.09
    èĻ±
    0.09
    æĿłæĿĨ
    0.09
    è¿ĺä¸įå¤Ł
    0.08
    ç¾İ好
    0.08
    è¾ĥ强çļĦ
    0.08
    StateToProps
    0.08
     Beaut
    0.08
    æĬĢèĥ½åŁ¹è®Ń
    0.08
    Activations Density 0.028%

    No Known Activations