© 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. 59172
    Prev
    Next
    INDEX
    Explanations

    IEEE standards

    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
    幺
    -0.10
    land
    -0.09
    -0.09
    åľ°å¸¦
    -0.09
    åijIJ
    -0.08
    /of
    -0.08
     ditch
    -0.08
    éĢĢç¨İ
    -0.07
    çģ
    -0.07
    lix
    -0.07
    POSITIVE LOGITS
    edly
    0.10
    .ie
    0.10
    ijk
    0.10
    -opt
    0.10
    .opens
    0.10
     Syracuse
    0.09
    çĮĽ
    0.09
    ä¿Ń
    0.09
    enes
    0.09
     окÑĢÑĥг
    0.09
    Activations Density 0.015%

    No Known Activations