© 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. 50834
    Prev
    Next
    INDEX
    Explanations

    Tim Burton’s, Guillermo del Toro’s

    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
    åįķ车
    -0.10
    çIJı
    -0.10
    ç¢
    -0.09
    çİ°å®ŀçĶŁæ´»
    -0.09
    ropolis
    -0.08
    æĮĿ
    -0.08
    å®ŀäºĭæ±Ĥæĺ¯
    -0.08
    NAL
    -0.08
    rieb
    -0.08
    uros
    -0.08
    POSITIVE LOGITS
    éħļ
    0.09
    hest
    0.09
    çĿ¡åīį
    0.09
    æŃ¦ä¾ł
    0.09
    ç¥Ģ
    0.09
     Sleeping
    0.08
    æĸĩåĮĸæĹħ游
    0.08
    å¥ģ
    0.08
    宫廷
    0.08
    rise
    0.08
    Activations Density 0.097%

    No Known Activations