© 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. 36583
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    à¹Į
    -0.09
    wer
    -0.09
    æĢİä¹ĪåĬŀ
    -0.09
    unner
    -0.08
     вÑģ
    -0.08
    çī¹åĪ«æĺ¯åľ¨
    -0.07
    imation
    -0.07
    ged
    -0.07
    ards
    -0.07
    ier
    -0.07
    POSITIVE LOGITS
    .FLAG
    0.10
    ä¸Ģé¢Ĺ
    0.09
    otlin
    0.09
     Trophy
    0.09
    .debugLine
    0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.09
    .Guna
    0.09
    çĬŁ
    0.09
    天ä¸Ĭ
    0.09
    æĤ£èĢħçļĦ
    0.09
    Activations Density 0.074%

    No Known Activations