© 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. 47797
    Prev
    Next
    INDEX
    Explanations

    competition and its effects

    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
    age
    -0.10
    oub
    -0.09
    ori
    -0.09
     uns
    -0.08
    oris
    -0.08
    orney
    -0.08
    cust
    -0.08
    uttle
    -0.08
    MIT
    -0.07
    /OR
    -0.07
    POSITIVE LOGITS
     fier
    0.13
     advantage
    0.11
    itors
    0.11
     Advantage
    0.11
    uml
    0.10
     fierce
    0.10
     edge
    0.10
    /conf
    0.10
     fringe
    0.10
     Edge
    0.10
    Activations Density 0.057%

    No Known Activations