© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53340
    Prev
    Next
    INDEX
    Explanations

    works composed or performed

    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
    äl
    -0.09
    astic
    -0.08
    èİ«æĸ¯
    -0.08
    æĿ¥èĩªäºİ
    -0.08
    æѦåĬŁ
    -0.07
     завод
    -0.07
    åIJ¦è®¤
    -0.07
    acoes
    -0.07
    .shtml
    -0.07
    vant
    -0.07
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    æĺ
    0.09
    åĪ°è´¦
    0.09
    é¹ľ
    0.09
    åĴĨ
    0.08
    èħ´
    0.08
    åľ©
    0.08
    ãĤ«ãĥ«
    0.08
    å¤įä»ĩ
    0.08
    otics
    0.08
    Activations Density 0.060%

    No Known Activations