© 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. 36618
    Prev
    Next
    INDEX
    Explanations

    atmospheric conditions or ground lines

    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
    åĩĨ
    -0.11
    ocus
    -0.10
    uci
    -0.09
    å¤Ń
    -0.09
    ç²¾åŃIJ
    -0.09
     Hud
    -0.09
    ä¸įç¡®å®ļæĢ§
    -0.09
    åģĩ
    -0.08
     ChÃŃnh
    -0.08
    apo
    -0.08
    POSITIVE LOGITS
    åĩĢèµĦ产
    0.11
    åĩĢåĢ¼
    0.10
    éĤij
    0.09
    éķĽ
    0.09
    lems
    0.08
    enburg
    0.08
    ETO
    0.08
    èĵĵ
    0.08
    红è±Ĩ
    0.08
    æŀ¶æŀĦ
    0.08
    Activations Density 0.039%

    No Known Activations