© 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. 59438
    Prev
    Next
    INDEX
    Explanations

    functionality and practicality

    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
    å®Įæķ´çļĦ
    -0.10
    æ²®
    -0.10
    å®Įæķ´
    -0.09
    phia
    -0.09
    åĸľ
    -0.09
    éķŃ
    -0.09
    .entries
    -0.09
    ofire
    -0.08
    足以
    -0.08
    IVER
    -0.08
    POSITIVE LOGITS
    å®ŀçĶ¨æĢ§
    0.20
    åĬŁèĥ½æĢ§
    0.19
    å®ŀçĶ¨
    0.18
    çļĦåĬŁèĥ½
    0.16
    åĬŁèĥ½
    0.15
     functionality
    0.14
     functional
    0.14
    åħ¼é¡¾
    0.12
    Functional
    0.12
    -functional
    0.12
    Activations Density 0.073%

    No Known Activations