© 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. 36849
    Prev
    Next
    INDEX
    Explanations

    thymidine, basil, house, norovirus

    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
    åīįéĢĶ
    -0.10
    enta
    -0.09
    irt
    -0.09
    olf
    -0.09
    è¦ģåѦä¼ļ
    -0.08
    rut
    -0.08
    å®ŀäºĭ
    -0.08
    æ¼Ķç»İ
    -0.08
    éĢļä¿Ĺ
    -0.08
    ×Ĺ׾ק
    -0.08
    POSITIVE LOGITS
    侯
    0.10
    coe
    0.10
    æľīè¿Ļæł·çļĦ
    0.10
    ANE
    0.08
    Ñħи
    0.08
    urn
    0.08
    -any
    0.08
    åĢĻ
    0.08
     bang
    0.08
    å¹»
    0.08
    Activations Density 0.003%

    No Known Activations