© 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. 112090
    Prev
    Next
    INDEX
    Explanations

    modelproduct model numbers

    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
     dere
    -0.10
    ROI
    -0.10
    <small
    -0.09
     equivalence
    -0.09
     Jerseys
    -0.08
    _means
    -0.08
     equivalent
    -0.08
    hiba
    -0.08
     verg
    -0.08
    wil
    -0.08
    POSITIVE LOGITS
     Deluxe
    0.11
     thankfully
    0.10
     unnamed
    0.09
     ($
    0.09
     sports
    0.09
     belongs
    0.09
     unfavor
    0.09
    minus
    0.08
     itself
    0.08
    itty
    0.08
    Activations Density 0.116%

    No Known Activations