© 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. 88145
    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
     begr
    -0.10
     Ah
    -0.10
     arg
    -0.09
    toa
    -0.09
     millionaire
    -0.09
    ows
    -0.09
     neighbour
    -0.09
    simp
    -0.09
    owns
    -0.09
    beck
    -0.09
    POSITIVE LOGITS
    /ph
    0.09
    berman
    0.09
     Civil
    0.09
    istrict
    0.08
     batch
    0.08
    Catch
    0.08
     Dias
    0.08
    (unit
    0.08
    ervo
    0.08
    otel
    0.08
    Activations Density 0.000%

    No Known Activations