© 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. 56312
    Prev
    Next
    INDEX
    Explanations

    shopping cart

    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
    éĻį
    -0.10
    åįĩåĢ¼
    -0.09
    çīĩ
    -0.08
    æ¶Ĥ
    -0.08
    á»ijt
    -0.08
     trá»Ŀi
    -0.08
    带头
    -0.08
    ilton
    -0.08
    çĸ¥
    -0.08
    æ°´æºIJ
    -0.08
    POSITIVE LOGITS
     Basket
    0.16
     basket
    0.15
     cart
    0.15
    篮
    0.15
    Cart
    0.14
     Cart
    0.14
    .cart
    0.13
    Basket
    0.13
     CART
    0.12
     carts
    0.12
    Activations Density 0.044%

    No Known Activations