© 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. 87918
    Prev
    Next
    INDEX
    Explanations

    how much

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cha
    -0.10
     dich
    -0.10
     bout
    -0.10
    pedia
    -0.09
    inki
    -0.09
     unfold
    -0.09
    fold
    -0.09
     Tear
    -0.08
     accumulated
    -0.08
     inflamm
    -0.08
    POSITIVE LOGITS
     longer
    0.12
    vari
    0.12
     variability
    0.11
     kr
    0.10
     variation
    0.10
     Longer
    0.09
     longest
    0.09
    assin
    0.09
    asy
    0.09
     Urs
    0.09
    Activations Density 0.004%

    No Known Activations