© 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. 49680
    Prev
    Next
    INDEX
    Explanations

    35 percent

    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
     stacked
    -0.09
    osate
    -0.09
    åijĺ
    -0.08
    äch
    -0.08
    bai
    -0.08
     stocking
    -0.08
    rying
    -0.08
    opian
    -0.08
    imiento
    -0.08
    imson
    -0.08
    POSITIVE LOGITS
    vet
    0.10
    -league
    0.10
    ifer
    0.10
    onica
    0.10
    .jackson
    0.10
    ifen
    0.09
    urer
    0.09
    pipe
    0.09
    vim
    0.09
     legit
    0.09
    Activations Density 0.124%

    No Known Activations