© 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. 91095
    Prev
    Next
    INDEX
    Explanations

    colon, punctuation, or sentence ending

    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
     Sus
    -0.09
    utils
    -0.08
     spurred
    -0.08
     Marino
    -0.08
     div
    -0.08
     compt
    -0.08
     rt
    -0.08
    anim
    -0.08
    /TR
    -0.08
     prive
    -0.08
    POSITIVE LOGITS
    "},"
    0.10
     what
    0.09
    !*
    0.09
    «
    0.09
    \f
    0.09
     Furn
    0.09
     stere
    0.09
     whom
    0.09
     nich
    0.09
    545
    0.09
    Activations Density 0.010%

    No Known Activations