© 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. 50585
    Prev
    Next
    INDEX
    Explanations

    what it seems

    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
     Kov
    -0.11
    032
    -0.10
    ASF
    -0.10
    uja
    -0.10
    aji
    -0.10
     disputed
    -0.09
    /article
    -0.09
    ffe
    -0.09
     contested
    -0.09
     Lakes
    -0.09
    POSITIVE LOGITS
     Mens
    0.09
     Buchanan
    0.08
     Buen
    0.08
    pret
    0.08
    omic
    0.08
    ullo
    0.07
     Punch
    0.07
     Rounds
    0.07
     Kata
    0.07
    izi
    0.07
    Activations Density 0.006%

    No Known Activations