© 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. 7309
    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
     founding
    -0.11
    onden
    -0.09
     CBC
    -0.08
     Lips
    -0.08
     ing
    -0.08
     pu
    -0.08
     Bru
    -0.08
    ward
    -0.08
    .kode
    -0.08
     Pat
    -0.08
    POSITIVE LOGITS
    mani
    0.09
    esco
    0.09
     EXTRA
    0.09
     Seymour
    0.09
     svens
    0.09
    drv
    0.09
     Nom
    0.08
     Isles
    0.08
     Shepard
    0.08
    yat
    0.08
    Activations Density 0.000%

    No Known Activations