© 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. 51982
    Prev
    Next
    INDEX
    Explanations

    may be

    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
    ооÑĢ
    -0.11
    ãģ¿
    -0.09
    eren
    -0.09
    ä¹Łä¸įåı¯èĥ½
    -0.08
    åĩłä¹İ
    -0.08
    ãģıãĤĭ
    -0.08
     Nug
    -0.08
    arily
    -0.08
    æĺ¯ä¸įåı¯èĥ½
    -0.08
    oving
    -0.08
    POSITIVE LOGITS
    haps
    0.13
    è¿Ļæīįæĺ¯
    0.11
    ÑĤÑĮ
    0.11
    wel
    0.10
    -times
    0.10
    æŃ£åĽłä¸º
    0.10
    æĺ¯åľ¨
    0.10
    åīįä¸ĸ
    0.10
    æݾ
    0.09
    -être
    0.09
    Activations Density 0.047%

    No Known Activations