© 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. 7809
    Prev
    Next
    INDEX
    Explanations

    state of affairs

    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
    ç»ıèIJ¥èĮĥåĽ´
    -0.09
    acy
    -0.09
    หลวà¸ĩ
    -0.09
    两ä¼ļ
    -0.08
    让大家
    -0.08
    ../../../
    -0.08
     sát
    -0.08
    غÙĪ
    -0.08
    تÙĦ
    -0.08
    anton
    -0.08
    POSITIVE LOGITS
    æħĭ
    0.16
    MENTS
    0.13
    æĢģ
    0.13
     quo
    0.11
    åIJĦå¼Ĥ
    0.10
    ä¸ĩåįĥ
    0.10
    çĬ¶æĢģ
    0.10
    (newState
    0.10
    ãģ¾ãģ¾
    0.09
    quo
    0.09
    Activations Density 0.082%

    No Known Activations