© 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. 52093
    Prev
    Next
    INDEX
    Explanations

    holding refrigerator, shop, or it

    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
    orst
    -0.09
    触åıĬ
    -0.09
    æģ½
    -0.09
    æijŀ
    -0.09
    èįĥ
    -0.08
     Pry
    -0.08
    çļĵ
    -0.08
     decrement
    -0.08
    èĽ²
    -0.08
    prt
    -0.08
    POSITIVE LOGITS
    æµĵ缩
    0.10
    æ´½
    0.10
    åŃĺæĶ¾
    0.10
    bit
    0.09
     bit
    0.08
    -properties
    0.08
    erate
    0.08
    çĵ¶
    0.08
    çģĮ
    0.08
     ÑħÑĢ
    0.08
    Activations Density 0.030%

    No Known Activations