© 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. 30740
    Prev
    Next
    INDEX
    Explanations

    known to

    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
    dae
    -0.11
    dam
    -0.09
    da
    -0.09
    dt
    -0.09
    tone
    -0.09
    di
    -0.09
    dos
    -0.09
    do
    -0.08
    top
    -0.08
     ent
    -0.08
    POSITIVE LOGITS
     fact
    0.14
    ledge
    0.13
    s
    0.12
     known
    0.12
     Bates
    0.12
     quantity
    0.11
     quantities
    0.11
    Known
    0.10
     Known
    0.10
     Bold
    0.10
    Activations Density 0.146%

    No Known Activations