© 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. 55799
    Prev
    Next
    INDEX
    Explanations

    EL expressions, List, Pi status, Column, magic numbers, Hern, women, foreach, gene expression, mitochondrial diseases

    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
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    ä¸įçĦ¶
    -0.09
    Ñīа
    -0.09
    å½¹
    -0.09
    åIJ¦åĪĻ
    -0.08
     otherwise
    -0.08
    家ä¼Ļ
    -0.08
    çľĭä½ł
    -0.08
    åĽ°æī°
    -0.08
    ç»ĻäºĨ
    -0.08
    POSITIVE LOGITS
    ç¿ķ
    0.11
    è¤Ĥ
    0.10
    icans
    0.09
    ä¸įäºĨ
    0.09
    ofday
    0.09
    awi
    0.09
    æĺ¥æĻļ
    0.09
    å¯ĵ
    0.08
    zes
    0.08
    isans
    0.08
    Activations Density 1.539%

    No Known Activations