© 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. 26468
    Prev
    Next
    INDEX
    Explanations

    distributed, managed, part, licensed, offering, free

    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
    /share
    -0.11
    igua
    -0.11
     Bulg
    -0.10
    amus
    -0.10
     "'",
    -0.10
    asca
    -0.10
    abort
    -0.10
     Consort
    -0.10
    ;)
    -0.10
    Observers
    -0.10
    POSITIVE LOGITS
    ovel
    0.08
     unlike
    0.07
     Nag
    0.07
    abal
    0.07
     -$
    0.07
    available
    0.07
     enjoyed
    0.06
     CEL
    0.06
    u
    0.06
     Fab
    0.06
    Activations Density 0.003%

    No Known Activations