© 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. 27161
    Prev
    Next
    INDEX
    Explanations

    names ending in i (or by, mi, ri, ni)

    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
    conc
    -0.10
    brid
    -0.09
     Padding
    -0.09
    illow
    -0.09
    orgh
    -0.09
     infra
    -0.09
    -FIRST
    -0.09
    amel
    -0.09
     Pend
    -0.09
     reputed
    -0.09
    POSITIVE LOGITS
    lyn
    0.10
    ilyn
    0.10
    elyn
    0.10
    nie
    0.10
    orno
    0.09
     Montana
    0.09
    ney
    0.09
     Lynn
    0.09
    frey
    0.08
    elle
    0.08
    Activations Density 0.022%

    No Known Activations