© 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. 16780
    Prev
    Next
    INDEX
    Explanations

    everything included

    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
    Ñıн
    -0.09
    éĨª
    -0.08
    boro
    -0.08
    anonymous
    -0.08
    Nib
    -0.08
     Hubbard
    -0.08
    éĿłè¿ij
    -0.08
    buster
    -0.08
    两åı¥
    -0.08
    holm
    -0.08
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.13
    å®Įæķ´
    0.12
    å®Įæķ´çļĦ
    0.12
     intact
    0.12
     including
    0.11
    åľ¨åĨħçļĦ
    0.11
    åħ¨éĥ¨
    0.11
    åĮħæĭ¬
    0.11
    ä¸Ģ举
    0.10
    ä¸ĢåĪĩ
    0.10
    Activations Density 0.120%

    No Known Activations