© 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. 6961
    Prev
    Next
    INDEX
    Explanations

    making habits, smart homes, professional sports, design

    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
    è¾ĺ
    -0.10
    èĩªçĦ¶èĢĮ
    -0.10
    éĦ¢
    -0.10
    çļĦ女åĦ¿
    -0.10
    çĻ½èıľ
    -0.09
    æĺİæľĹ
    -0.09
    åĩĢåĪ©æ¶¦
    -0.09
    åĴĮåľ°åĮº
    -0.09
    积èĵĦ
    -0.09
    éĴ¹
    -0.09
    POSITIVE LOGITS
    çŃīçŃī
    0.09
    羨
    0.08
    é¦ĸ
    0.08
    çĶµèĦij
    0.08
    (tol
    0.07
    ioni
    0.07
    oggle
    0.07
    hea
    0.07
     vs
    0.07
     etc
    0.07
    Activations Density 0.709%

    No Known Activations