© 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. 27981
    Prev
    Next
    INDEX
    Explanations

    email or article metadata

    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
     dem
    -0.09
    اÙģ
    -0.09
     Nack
    -0.08
     plat
    -0.07
    pta
    -0.07
     emails
    -0.07
     emailed
    -0.07
     hugs
    -0.07
     Explorer
    -0.07
     ens
    -0.07
    POSITIVE LOGITS
    adora
    0.10
     schem
    0.10
     volcano
    0.10
     Clayton
    0.09
    stdin
    0.09
    qd
    0.09
    tol
    0.09
    gmail
    0.09
     Russ
    0.09
     bergen
    0.09
    Activations Density 0.136%

    No Known Activations