© 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. 61885
    Prev
    Next
    INDEX
    Explanations

    contact us or in touch

    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
     Nigel
    -0.09
     Morr
    -0.09
    çĿĽ
    -0.08
    åĢ®
    -0.08
    è¡ĢèĦī
    -0.08
    æĪIJ绩åįķ
    -0.08
    aine
    -0.08
     bou
    -0.08
    æķ´å½¢
    -0.08
    (bp
    -0.08
    POSITIVE LOGITS
     chat
    0.12
     IRC
    0.11
    èģĬ天
    0.10
    å¿Ŀ
    0.10
    prech
    0.09
    éĤ¸
    0.09
    gens
    0.09
     irc
    0.09
    ä½ĵè´´
    0.09
    chat
    0.09
    Activations Density 0.119%

    No Known Activations