© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90332
    Prev
    Next
    INDEX
    Explanations

    .md file suffixes

    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
    edin
    -0.09
    oons
    -0.08
     contest
    -0.08
    dorf
    -0.08
     quo
    -0.08
     Templ
    -0.08
    Radians
    -0.08
    ç©
    -0.08
     Dickinson
    -0.08
     permanently
    -0.07
    POSITIVE LOGITS
     anymore
    0.12
    orage
    0.10
    öt
    0.10
    san
    0.10
    strap
    0.10
     Cres
    0.10
     reproduced
    0.10
    Stride
    0.10
    anness
    0.10
    chie
    0.09
    Activations Density 0.001%

    No Known Activations