© 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. 26661
    Prev
    Next
    INDEX
    Explanations

    loathe, loom, looney, loves, lorem, loiter

    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
    inar
    -0.11
    fel
    -0.11
    abh
    -0.10
     cram
    -0.10
     Buckingham
    -0.10
    Chelsea
    -0.10
    imento
    -0.09
    ISCO
    -0.09
    ummer
    -0.09
     airs
    -0.09
    POSITIVE LOGITS
     lo
    0.20
     Lo
    0.16
    -lo
    0.14
    (lo
    0.13
    Lo
    0.13
    _lo
    0.12
    .lo
    0.12
     Loch
    0.11
     loaf
    0.11
     loos
    0.11
    Activations Density 0.004%

    No Known Activations