© 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. 28714
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    aina
    -0.09
     Dana
    -0.09
     unp
    -0.08
    nek
    -0.08
     w
    -0.08
     page
    -0.08
     running
    -0.08
    ettel
    -0.08
    +(\
    -0.08
     showing
    -0.08
    POSITIVE LOGITS
    å¹´
    0.11
     å¹
    0.10
     anz
    0.10
    -ie
    0.10
     Vanity
    0.09
    fork
    0.09
     dyst
    0.09
    filt
    0.09
     Woodward
    0.09
     má
    0.09
    Activations Density 0.067%

    No Known Activations