© 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. 52783
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptive

    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
    INVAL
    -0.09
    åįĹéĺ³
    -0.09
    éļĶ离
    -0.09
    èĢĥãģĪ
    -0.09
    ç»Ļä»ĸ们
    -0.09
    çĿ¬
    -0.09
    -columns
    -0.08
    itag
    -0.08
    çħ§æł·
    -0.08
    .GL
    -0.08
    POSITIVE LOGITS
    åħļåĴĮ
    0.09
    ä¸įä¹ħ
    0.08
    飧
    0.08
    èŁij
    0.08
     Soon
    0.08
     soon
    0.08
    æĶ¿åħļ
    0.08
    æ°ijæĦı
    0.08
    æĻŁ
    0.08
    åĤ¬
    0.08
    Activations Density 0.242%

    No Known Activations