© 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. 47396
    Prev
    Next
    INDEX
    Explanations

    taking time or longer

    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
    ä¹ŁåºĶ该
    -0.09
     vandalism
    -0.09
    æĤŃ
    -0.09
    èĥ½åľ¨
    -0.09
    idon
    -0.08
     bạc
    -0.08
    _UL
    -0.08
    èļ©
    -0.08
    NCY
    -0.08
    egin
    -0.08
    POSITIVE LOGITS
    åĨľåī¯
    0.10
     rozwiÄħzania
    0.09
    沤
    0.08
    太ä¹ħ
    0.08
    PerPixel
    0.08
    产ä¸ļåįĩ级
    0.08
    èĤł
    0.08
    mos
    0.08
    lear
    0.08
    yan
    0.08
    Activations Density 0.020%

    No Known Activations