© 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. 12321
    Prev
    Next
    INDEX
    Explanations

    after followed by a temporal event

    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
     lean
    -0.09
    пÑĢод
    -0.08
     Lean
    -0.08
    sig
    -0.08
    éĻ¢
    -0.08
    amd
    -0.08
    Lean
    -0.08
     CI
    -0.08
    sg
    -0.08
    lean
    -0.08
    POSITIVE LOGITS
    å®ıè§Ĥ
    0.09
    æľĢè¿ij
    0.09
    次è¦ģ
    0.09
    åģ¥
    0.09
    é³ĸ
    0.09
    å¾Ĺ天
    0.08
    ismatic
    0.08
    è°Ł
    0.08
    åĪĿ级
    0.08
     Imperial
    0.08
    Activations Density 0.019%

    No Known Activations