© 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. 29174
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     shard
    -0.11
    /=
    -0.11
    /is
    -0.10
    _CS
    -0.10
    esch
    -0.10
     verr
    -0.09
    ürn
    -0.09
    /lic
    -0.09
    locator
    -0.09
    com
    -0.09
    POSITIVE LOGITS
    aine
    0.09
     Hag
    0.09
     Wade
    0.09
     imp
    0.08
     Intr
    0.08
    lw
    0.08
    .tm
    0.08
     intr
    0.08
     DOCUMENT
    0.08
    als
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.