© 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. 29942
    Prev
    Next
    INDEX
    Explanations

    daily, greatest common, multiple of, remainder when, 6 new, extract, ecg

    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
    vig
    -0.10
     accord
    -0.10
    [of
    -0.10
     Sears
    -0.10
     Tennis
    -0.10
     fractional
    -0.09
    avn
    -0.09
    ixo
    -0.09
    antis
    -0.09
    fraction
    -0.09
    POSITIVE LOGITS
    rip
    0.08
     unknow
    0.08
     monthly
    0.08
     OO
    0.08
     approximate
    0.08
     perceptions
    0.08
     rent
    0.08
    Monthly
    0.08
     gross
    0.08
    cle
    0.07
    Activations Density 0.007%

    No Known Activations