© 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. 16788
    Prev
    Next
    INDEX
    Explanations

    foundation for building

    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
    çĭ¬å®¶
    -0.09
    eria
    -0.09
     stringify
    -0.08
    eri
    -0.08
    æ´½
    -0.08
    çķĮ
    -0.08
    åį°
    -0.08
    æĮĩå°ĸ
    -0.08
    linger
    -0.08
    ç³»åĪĹ产åĵģ
    -0.08
    POSITIVE LOGITS
    åĿļå®ŀçļĦ
    0.20
    åŁºç¡Ģ
    0.20
     foundation
    0.20
    åĿļå®ŀ
    0.19
     base
    0.19
    åŁºç¤İ
    0.18
    base
    0.17
     баз
    0.17
    夯å®ŀ
    0.16
    	base
    0.16
    Activations Density 0.040%

    No Known Activations