© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    The copyright and contents

    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
     freel
    -0.11
    antal
    -0.10
     Nad
    -0.10
     hindsight
    -0.10
    imed
    -0.09
     suburban
    -0.09
     footnote
    -0.09
     updated
    -0.09
     köz
    -0.09
     README
    -0.09
    POSITIVE LOGITS
     events
    0.13
     following
    0.11
     numbering
    0.11
     characters
    0.11
     views
    0.10
     names
    0.10
    ovah
    0.10
    -events
    0.10
     Organization
    0.09
     Prem
    0.09
    Activations Density 0.029%

    No Known Activations