© 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. 30205
    Prev
    Next
    INDEX
    Explanations

    review or test

    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
    iman
    -0.11
    itr
    -0.10
    .edu
    -0.10
     typename
    -0.10
     Barb
    -0.10
    ète
    -0.10
    VERS
    -0.10
    .fm
    -0.10
    edin
    -0.10
    coc
    -0.10
    POSITIVE LOGITS
     fac
    0.09
     ':
    0.09
     favoured
    0.09
     enclosed
    0.09
     mostly
    0.08
     outright
    0.08
     sme
    0.08
     vel
    0.08
     visually
    0.08
     experiment
    0.08
    Activations Density 0.001%

    No Known Activations