© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64046
    Prev
    Next
    INDEX
    Explanations

    widespread + negative consequence/situation

    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
    Negative Logits
    沤
    -0.09
    æµľ
    -0.09
    pus
    -0.09
    erve
    -0.08
    strap
    -0.08
    ä¸įä¸Ĭ
    -0.08
    ong
    -0.08
    StackSize
    -0.08
     türlü
    -0.08
    èij©
    -0.08
    POSITIVE LOGITS
    å¹¿æ³ĽçļĦ
    0.12
    èĶĵ延
    0.10
     widespread
    0.10
    弥漫
    0.10
    abouts
    0.10
    åľ»
    0.09
    好è¯Ħ
    0.09
    çݰ象
    0.09
    MENTS
    0.09
    å¹¿æ³Ľ
    0.09
    Activations Density 0.062%

    No Known Activations