© 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. 7053
    Prev
    Next
    INDEX
    Explanations

    cut / cutting

    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
     unrecognized
    -0.10
     reco
    -0.09
     pinch
    -0.08
    tober
    -0.08
    ê³µ
    -0.08
     Lowell
    -0.08
     Dillon
    -0.07
     Gilles
    -0.07
     Zuk
    -0.07
    iers
    -0.07
    POSITIVE LOGITS
    amic
    0.11
     stimulation
    0.10
    lass
    0.10
    ely
    0.10
     trimmed
    0.10
    ies
    0.10
    trimmed
    0.10
     hous
    0.10
    icular
    0.09
     ushort
    0.09
    Activations Density 0.001%

    No Known Activations