© 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. 25361
    Prev
    Next
    INDEX
    Explanations

    CRM, path, db, platform, customers

    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
     inex
    -0.10
    /check
    -0.10
    een
    -0.10
    ta
    -0.09
    cord
    -0.09
    ogi
    -0.09
    tons
    -0.09
     undone
    -0.09
    cut
    -0.09
    cs
    -0.09
    POSITIVE LOGITS
    '
    0.11
    ’
    0.11
    s
    0.10
    .com
    0.10
    .ca
    0.09
    oble
    0.09
     noble
    0.09
    owi
    0.08
    Roger
    0.08
    imity
    0.08
    Activations Density 0.004%

    No Known Activations