© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111429
    Prev
    Next
    INDEX
    Explanations

    words ending in "ass", "ocker", "anker", "ool", "irl"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     ladies
    -0.09
    ?")↵
    -0.09
     respectively
    -0.09
     declar
    -0.09
    OB
    -0.08
    onn
    -0.08
    ?";↵
    -0.08
    &amp
    -0.08
     enn
    -0.08
     Shi
    -0.08
    POSITIVE LOGITS
     shouldn
    0.11
    !
    0.11
     barely
    0.10
     Alert
    0.10
     overd
    0.10
     deserved
    0.10
     doesn
    0.10
     practically
    0.10
     virtually
    0.10
    uzzi
    0.10
    Activations Density 0.010%

    No Known Activations