© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8925
    Prev
    Next
    INDEX
    Explanations

    anime series related to martial arts and superpowers

    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
     gre
    -0.09
     analytics
    -0.08
    ä¿¡è´·
    -0.08
     Neon
    -0.08
    åĽ½å®¶å®īåħ¨
    -0.08
    ä½ĵéĩı
    -0.07
     AP
    -0.07
     ju
    -0.07
     neon
    -0.07
    ÂŃs
    -0.07
    POSITIVE LOGITS
    çĵ¢
    0.10
    åºŁæŧ
    0.10
    è¹Ī
    0.09
    .spin
    0.09
    æĨ§æĨ¬
    0.09
    ç´«èī²
    0.09
    伺
    0.09
    éĵĹ
    0.09
    使ä¹ĭ
    0.09
    åĵĦ
    0.09
    Activations Density 0.194%

    No Known Activations