© 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. 2154
    Prev
    Next
    INDEX
    Explanations

    sql FROM clause with table names

    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
    éĥ½åľ¨
    -0.10
    ä»Ĺ
    -0.09
    åĸľ
    -0.09
    éĥĵ
    -0.09
    询éĹ®
    -0.08
    Tre
    -0.08
    åĩ¯
    -0.08
    tre
    -0.08
    è¹
    -0.08
    usi
    -0.08
    POSITIVE LOGITS
     Lexington
    0.09
    ä¸Ģä¸ĭåŃIJå°±
    0.09
    èıģ
    0.09
    unded
    0.08
     hers
    0.08
    asso
    0.08
    ycz
    0.08
    æĸ°çļĦä¸Ģ
    0.08
    å¾Ģä¸Ĭ
    0.08
    _FEATURE
    0.08
    Activations Density 0.012%

    No Known Activations