© 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. 51937
    Prev
    Next
    INDEX
    Explanations

    bargains and deals

    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
    循
    -0.09
    å¯Ħ
    -0.09
    å¾Ĥ
    -0.09
    æijĩ
    -0.09
    æ²
    -0.09
    ç½ijç»ľä¼łæĴŃ
    -0.09
     бил
    -0.09
    пÑĥÑģ
    -0.09
    ousse
    -0.08
     Mund
    -0.08
    POSITIVE LOGITS
    æīĵæĬĺ
    0.12
     barg
    0.12
     bargain
    0.11
    æĬĺæī£
    0.11
    ä¼ĺæĥł
    0.11
    ãģĬå¾Ĺ
    0.09
    åĦªæĥł
    0.09
     deals
    0.09
     deal
    0.09
    èѦ
    0.09
    Activations Density 0.050%

    No Known Activations