© 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. 32691
    Prev
    Next
    INDEX
    Explanations

    alternative or closest

    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
    aurus
    -0.10
     Gur
    -0.09
    Simply
    -0.09
    adal
    -0.09
    acious
    -0.08
     Grape
    -0.08
     Barnett
    -0.08
     outlier
    -0.08
     NaN
    -0.08
    wal
    -0.08
    POSITIVE LOGITS
     substitute
    0.27
     substitutes
    0.26
     Close
    0.26
     close
    0.26
     equivalent
    0.26
     closest
    0.25
    Close
    0.22
     equally
    0.22
     substituted
    0.22
    close
    0.22
    Activations Density 0.232%

    No Known Activations