© 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. 29626
    Prev
    Next
    INDEX
    Explanations

    names, paths, national debt

    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
     elm
    -0.14
    ema
    -0.13
    EM
    -0.13
    EMA
    -0.13
     Elm
    -0.13
     EM
    -0.12
    eman
    -0.12
    el
    -0.12
    elden
    -0.12
    ELL
    -0.12
    POSITIVE LOGITS
     MES
    0.16
     Ves
    0.16
     wes
    0.16
     Hess
    0.15
     Nes
    0.15
    ester
    0.15
     Bert
    0.15
     bert
    0.14
    ernet
    0.14
    BEST
    0.14
    Activations Density 0.246%

    No Known Activations