© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10797
    Prev
    Next
    INDEX
    Explanations

    relegation and promotion

    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
    ç»
    -0.09
    ฤ
    -0.08
    æł¡å¤ĸ
    -0.08
    绶
    -0.08
    æ°Ķè´¨
    -0.08
    ertest
    -0.08
    æĶ¾åģĩ
    -0.08
    æ·ŀ
    -0.08
    æ¹¾åĮº
    -0.08
    åģĩæľŁ
    -0.08
    POSITIVE LOGITS
     Robbins
    0.10
    -strip
    0.10
    cul
    0.10
    ë°Ľ
    0.09
    بÙĬÙĨ
    0.09
    åį´è¢«
    0.08
    رج
    0.08
    orus
    0.08
    åı¯èĥ½æĢ§
    0.08
    ÐļÑĥÑĢÑģ
    0.08
    Activations Density 0.006%

    No Known Activations