© 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. 117281
    Prev
    Next
    INDEX
    Explanations

    you expecting or asking

    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
    orris
    -0.10
    kie
    -0.10
    abi
    -0.09
     Lovely
    -0.09
     jointly
    -0.09
    Cpp
    -0.09
     myself
    -0.09
    assic
    -0.09
    ansa
    -0.09
    WARN
    -0.09
    POSITIVE LOGITS
     admit
    0.12
     finally
    0.10
     Peters
    0.10
     saying
    0.10
     ARE
    0.10
    bas
    0.10
     GAM
    0.10
     admits
    0.10
     admitting
    0.09
    è´
    0.09
    Activations Density 0.011%

    No Known Activations