© 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. 9160
    Prev
    Next
    INDEX
    Explanations

    odds against, odds of, odds ratios

    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
    aps
    -0.09
    uchi
    -0.09
    åĽĽå¤§
    -0.09
    tion
    -0.09
    apult
    -0.08
    æİı
    -0.08
     Duis
    -0.08
    ä¸įæĥľ
    -0.08
    æĦıåIJij
    -0.08
    caret
    -0.08
    POSITIVE LOGITS
     odds
    0.10
    Against
    0.10
    ä¸įåıĺ
    0.09
     пÑĢоÑĨ
    0.09
    éŀĺ
    0.09
    ashi
    0.09
    çŃĴ
    0.08
    è¢ľ
    0.08
    ä¸ĭ次
    0.08
    licer
    0.08
    Activations Density 0.008%

    No Known Activations