© 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. 36641
    Prev
    Next
    INDEX
    Explanations

    wall or crown molding

    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
    å¾Ĥ
    -0.10
     crossings
    -0.09
    placed
    -0.09
    çıī
    -0.09
    tal
    -0.09
     contr
    -0.09
    éķ«
    -0.09
    åģļä¸ĢäºĽ
    -0.09
     WARRANTIES
    -0.08
     chir
    -0.08
    POSITIVE LOGITS
    å£ģ
    0.14
    æ´»
    0.09
    å¢Ļ
    0.09
    åŀŃ
    0.08
    éĶĻ
    0.08
    çīĨ
    0.08
    å±ħ室
    0.08
    pherd
    0.08
     wall
    0.08
    éģĵå¾·
    0.08
    Activations Density 0.110%

    No Known Activations