© 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. 18376
    Prev
    Next
    INDEX
    Explanations

    final difference

    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
     ultimately
    -0.19
     eventually
    -0.18
     finally
    -0.18
     eventual
    -0.17
    finally
    -0.13
     Eventually
    -0.12
     Ultimately
    -0.12
     Finally
    -0.12
    Finally
    -0.11
    Eventually
    -0.10
    POSITIVE LOGITS
    -pt
    0.11
    maids
    0.11
    oga
    0.10
     Britt
    0.09
     RM
    0.09
    ogo
    0.09
     Urs
    0.09
    ane
    0.09
    baugh
    0.09
     Wahl
    0.09
    Activations Density 0.057%

    No Known Activations