© 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. 15253
    Prev
    Next
    INDEX
    Explanations

    dates in dd/mm/yy or dd.mm.yyyy formats

    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
     Pot
    -0.11
    lys
    -0.11
    Tor
    -0.11
    stad
    -0.10
    /Game
    -0.09
    olia
    -0.09
     Torres
    -0.09
     Tor
    -0.09
    udd
    -0.09
    Serialization
    -0.09
    POSITIVE LOGITS
     May
    0.16
     November
    0.15
     April
    0.15
     Feb
    0.15
     Dec
    0.15
     January
    0.15
     February
    0.15
     December
    0.15
     March
    0.14
     Sep
    0.14
    Activations Density 0.144%

    No Known Activations