© 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. 36584
    Prev
    Next
    INDEX
    Explanations

    oxygen delivery

    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
    å½ĵåľ°äºº
    -0.10
    é«ĺè´µ
    -0.09
     poo
    -0.09
    åIJģ
    -0.09
    Invoker
    -0.09
    æ¿ij
    -0.09
    大家ä¸Ģèµ·
    -0.09
    ÑĦон
    -0.08
    rne
    -0.08
    _LOC
    -0.08
    POSITIVE LOGITS
    éħ£
    0.09
    åĪ°æĿ¥
    0.09
    æĥ¯
    0.09
    åĪĽéĢłæĢ§
    0.09
    åĪ°ä½į
    0.08
    è¾±
    0.08
     vu
    0.08
    临
    0.08
    vu
    0.08
    çļĦå°±æĺ¯
    0.08
    Activations Density 0.088%

    No Known Activations