© 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. 17938
    Prev
    Next
    INDEX
    Explanations

    February in dates

    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
    sey
    -0.11
    dess
    -0.11
    apa
    -0.09
    pieces
    -0.09
    front
    -0.08
    frm
    -0.08
    afort
    -0.08
     Gors
    -0.08
    orney
    -0.08
     inex
    -0.08
    POSITIVE LOGITS
    bruary
    0.15
    vrier
    0.15
    uary
    0.14
    lobal
    0.12
    RU
    0.12
    itor
    0.11
     February
    0.10
    Feb
    0.10
    February
    0.10
     January
    0.09
    Activations Density 0.052%

    No Known Activations