© 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. 2878
    Prev
    Next
    INDEX
    Explanations

    acceptance and support

    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
     unseen
    -0.09
     Cindy
    -0.09
    à¸ģาย
    -0.08
    æIJ¶
    -0.08
     Daisy
    -0.08
    çľĭä¸įè§ģ
    -0.08
    说æĺİ
    -0.08
     UserController
    -0.08
    (Controller
    -0.08
    好åIJĹ
    -0.08
    POSITIVE LOGITS
    åĮħ容
    0.13
    åºĩ
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    atron
    0.10
    毡
    0.09
    æݥ纳
    0.09
    温æļĸ
    0.09
    æĶ¯æĮģ
    0.09
    æѧè§Ĩ
    0.09
    éĻªä¼´
    0.09
    Activations Density 0.101%

    No Known Activations