© 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. 7837
    Prev
    Next
    INDEX
    Explanations

    work and labor

    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
    访
    -0.09
    é¡·
    -0.09
    温æŁĶ
    -0.08
    é¢ģ
    -0.08
    COPE
    -0.08
    ä¸Ģ次æĢ§
    -0.08
    emet
    -0.08
    溢
    -0.08
    ç§ī
    -0.08
    uly
    -0.08
    POSITIVE LOGITS
    å½¹
    0.14
    åĬ³åĬ¨
    0.13
    å·¥ä½ľ
    0.12
    _ctxt
    0.11
    å·¥ä½ľçļĦ
    0.11
    åĥį
    0.10
     labour
    0.10
    ä»ĺåĩº
    0.10
    å¾Ń
    0.10
    Harness
    0.10
    Activations Density 0.077%

    No Known Activations