© 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. 21239
    Prev
    Next
    INDEX
    Explanations

    in a vehicle, refrigerator, trunk, backpack

    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
    为主
    -0.10
    odom
    -0.10
    ç§
    -0.09
    ople
    -0.09
    isle
    -0.09
     Dro
    -0.09
    éĤª
    -0.08
    Sdk
    -0.08
    hop
    -0.08
    ç»´æĮģ
    -0.08
    POSITIVE LOGITS
    æ¼Ĥæµģ
    0.10
    /documentation
    0.10
    æIJĵ
    0.09
    é£Ļ
    0.09
    éıĸ
    0.09
    æĹ¥å¸¸çĶŁæ´»
    0.09
    èķĬ
    0.09
    pins
    0.09
    éĺ²æ°´
    0.08
    åĬłçĥŃ
    0.08
    Activations Density 0.061%

    No Known Activations