© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    achievement motivation goal

    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
    иÑĢование
    -0.10
    æĶ»åĬ¿
    -0.10
    æł·çļĦ
    -0.10
    èĩ¾
    -0.09
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    ORT
    -0.09
    ibly
    -0.09
    ething
    -0.09
    常å§Ķ
    -0.09
    åĩºèº«
    -0.09
    POSITIVE LOGITS
    æĸIJ
    0.12
    arian
    0.10
    人士
    0.10
     Trident
    0.10
    suming
    0.09
    ments
    0.09
    arium
    0.09
    ê±°
    0.09
    çĺķ
    0.09
    зн
    0.08
    Activations Density 0.020%

    No Known Activations