© 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. 55363
    Prev
    Next
    INDEX
    Explanations

    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
    æľīè¿Ļæł·çļĦ
    -0.09
    ous
    -0.09
    æľºéģĩ
    -0.09
    ered
    -0.08
    allest
    -0.08
    åĩ«
    -0.08
    #ga
    -0.08
     ÐĺнÑĤеÑĢ
    -0.08
    uka
    -0.08
    estre
    -0.08
    POSITIVE LOGITS
    ä½İä¸ĭ
    0.12
    effective
    0.10
    èĬĤçľģ
    0.10
    æķĪçİĩ
    0.10
    æķĪèĥ½
    0.10
     ÑĥпÑĢавлениÑı
    0.10
    å·¥ä½ľæķĪçİĩ
    0.09
    æľīæķĪ
    0.09
    æľīæķĪçļĦ
    0.09
     controls
    0.09
    Activations Density 0.126%

    No Known Activations