© 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. 49404
    Prev
    Next
    INDEX
    Explanations

    size, duration, or quantity

    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
     Stein
    -0.11
    iland
    -0.10
     erfolgre
    -0.09
     keinen
    -0.09
    %=
    -0.09
     gri
    -0.09
    prep
    -0.09
     Abb
    -0.08
    unya
    -0.08
     bisher
    -0.08
    POSITIVE LOGITS
     alive
    0.13
     stature
    0.11
     professionally
    0.11
     tall
    0.10
     size
    0.10
     wee
    0.10
     in
    0.10
     Zub
    0.10
     incarn
    0.09
     caliber
    0.09
    Activations Density 0.113%

    No Known Activations