© 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. 51149
    Prev
    Next
    INDEX
    Explanations

    upcoming movies and projects

    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
    享çĶ¨
    -0.11
    ä¸ĬäºĨ
    -0.11
    ç»ĻäºĨæĪij
    -0.10
    .rep
    -0.10
    äºĨä¸Ģä¸ĭ
    -0.09
    fur
    -0.09
    ippy
    -0.09
    åľĨ满å®ĮæĪIJ
    -0.09
    åıĤåĬłäºĨ
    -0.09
    èĩªæĪij
    -0.09
    POSITIVE LOGITS
    å°Ĩåľ¨
    0.15
    åĪ°æŶåĢĻ
    0.15
    å°Ĩäºİ
    0.14
     upcoming
    0.13
    å±ĬæŶ
    0.13
     forthcoming
    0.13
    å°Ĩä¼ļ
    0.13
    å°Ĩæĺ¯
    0.12
    æĺİå¹´
    0.12
    å¾Īåı¯èĥ½
    0.12
    Activations Density 0.186%

    No Known Activations