© 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. 60550
    Prev
    Next
    INDEX
    Explanations

    any given point

    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
    é¢ij
    -0.10
    çĵ£
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    å¹´åIJİ
    -0.09
    å¹´åīį
    -0.08
    éł»
    -0.08
    .createFrom
    -0.08
    _sold
    -0.08
    osl
    -0.08
    é«ĺ级
    -0.08
    POSITIVE LOGITS
     particular
    0.20
     given
    0.18
    given
    0.14
    æŁIJ个
    0.12
     particul
    0.11
    _given
    0.11
     PARTICULAR
    0.11
    æŁIJä¸Ģ
    0.11
     Given
    0.11
    Given
    0.11
    Activations Density 0.071%

    No Known Activations