© 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. 49100
    Prev
    Next
    INDEX
    Explanations

    truly followed by positive descriptors

    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
    æĺİæĺİ
    -0.10
    odo
    -0.10
    adesh
    -0.08
    å¾Ī好
    -0.08
    å¹²åĺĽ
    -0.08
    ç«ĭåľº
    -0.08
    ennon
    -0.08
    严éĩįå½±åĵį
    -0.08
    èijĹåIJį
    -0.08
    åģļ人
    -0.07
    POSITIVE LOGITS
    åĢ¼å¾Ĺåħ³æ³¨
    0.11
    åĢ¼å¾Ĺ
    0.11
    åĢ¼å¾Ĺä¸Ģ
    0.11
    åħĪè¡Į
    0.09
     Truly
    0.09
    çĭ¬ä¸ĢæĹłäºĮ
    0.09
     Worth
    0.09
    éķ¶åµĮ
    0.09
    æĺ¯ä¸Ģ件
    0.09
    åĽŀåĪ°äºĨ
    0.09
    Activations Density 0.017%

    No Known Activations