© 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. 52345
    Prev
    Next
    INDEX
    Explanations

    interested in

    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
    SEN
    -0.09
    ä¸įæĪIJ
    -0.09
    ä¸į容æĺĵ
    -0.09
    ilar
    -0.08
    访éĹ®
    -0.08
    SENS
    -0.08
    ille
    -0.08
    ä¸įåı¯ä»¥
    -0.08
     sinus
    -0.08
    ustin
    -0.08
    POSITIVE LOGITS
    æĦŁåħ´è¶£
    0.12
    çļĦåħ´è¶£
    0.12
    æĪļ
    0.10
    æĥ³çŁ¥éģĵ
    0.10
    å·²ä¹ħ
    0.10
     outcome
    0.10
    åıªæĥ³
    0.10
     ê´Ģìĭ¬
    0.09
    ä¹Łä¸įæĥ³
    0.09
     interests
    0.09
    Activations Density 0.047%

    No Known Activations