© 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. 9212
    Prev
    Next
    INDEX
    Explanations

    Google sheets

    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
    çĦ±
    -0.10
    itan
    -0.10
     Vân
    -0.10
    æĽ¼
    -0.09
    ä¹ĭéģĵ
    -0.09
    æĹ¶å¸¸
    -0.09
    æĪĸå¤ļ
    -0.09
    æ¯ıå¹´éĥ½
    -0.09
    бил
    -0.09
    æĬļæij¸
    -0.08
    POSITIVE LOGITS
    çıŃ
    0.09
    okit
    0.09
    .opensource
    0.08
    èĪªæµ·
    0.08
    举
    0.08
    esub
    0.08
    è¯ĦåĪ¤
    0.08
    kul
    0.08
    èĬŃ
    0.08
    MLS
    0.07
    Activations Density 0.014%

    No Known Activations