© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 28000
    Prev
    Next
    INDEX
    Explanations

    efficiency and effectiveness

    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
    ulk
    -0.09
    åħ¨èĩªåĬ¨
    -0.08
    [op
    -0.08
    æłijç«ĭ
    -0.08
    å¥Ĺ
    -0.08
    è°Ł
    -0.08
    éĻ¬
    -0.08
    ç»į
    -0.08
    èĩªçIJĨ
    -0.08
     Spa
    -0.08
    POSITIVE LOGITS
    æķĪçİĩ
    0.30
     efficiency
    0.23
    æķĪèĥ½
    0.21
     ÑįÑĦÑĦекÑĤив
    0.21
    é«ĺæķĪ
    0.21
     effectiveness
    0.20
     efficient
    0.20
     Efficiency
    0.19
    é«ĺæķĪçļĦ
    0.19
    efficient
    0.18
    Activations Density 0.106%

    No Known Activations