© 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. 34119
    Prev
    Next
    INDEX
    Explanations

    numerals followed by hyphens

    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
     Oliv
    -0.10
     defe
    -0.09
    CI
    -0.08
     sh
    -0.08
     cro
    -0.08
     Fluent
    -0.08
     pol
    -0.08
    imi
    -0.08
     ðŁĻĤ
    -0.08
     Mim
    -0.08
    POSITIVE LOGITS
    htag
    0.09
    ...");↵↵
    0.09
     tack
    0.09
    ixo
    0.09
    aska
    0.09
    >↵↵↵↵↵
    0.09
    (END
    0.09
    ailable
    0.09
    lian
    0.09
    Contrib
    0.08
    Activations Density 0.001%

    No Known Activations