© 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. 20784
    Prev
    Next
    INDEX
    Explanations

    end of script

    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
    è¢
    -0.10
    icol
    -0.10
    åŦ
    -0.09
    ä¸įåħ¬å¹³
    -0.09
    纨
    -0.09
    ä¸įå®Į
    -0.09
    lesh
    -0.08
    ific
    -0.08
     Nun
    -0.08
    Ñħож
    -0.08
    POSITIVE LOGITS
    尽头
    0.10
    ç©·
    0.10
    è¾¾åĪ°äºĨ
    0.10
    æĺ¯çľŁçļĦ
    0.09
    æŁĶ
    0.09
    æģŃ
    0.09
    窮
    0.09
    .setVertical
    0.09
    åĿı
    0.09
    æłĩå¿Ĺ
    0.09
    Activations Density 0.069%

    No Known Activations