© 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. 25973
    Prev
    Next
    INDEX
    Explanations

    most out of / best experience

    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
    amas
    -0.12
    aders
    -0.12
     extensively
    -0.12
    oft
    -0.11
    anni
    -0.11
    /Internal
    -0.11
     Alec
    -0.11
    orris
    -0.11
    place
    -0.11
    ften
    -0.11
    POSITIVE LOGITS
     bang
    0.13
     possible
    0.12
     benefit
    0.11
     maximum
    0.11
     value
    0.11
     benefits
    0.11
     out
    0.11
     optimum
    0.10
     experience
    0.10
     coverage
    0.09
    Activations Density 0.065%

    No Known Activations