© 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. 89256
    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
    hive
    -0.10
    immer
    -0.10
     dre
    -0.10
    iola
    -0.10
    ignite
    -0.09
    hev
    -0.09
    \a
    -0.09
    ffects
    -0.09
     liber
    -0.09
    verity
    -0.09
    POSITIVE LOGITS
     bol
    0.08
    lauf
    0.08
    Nova
    0.08
     thereof
    0.08
    ilst
    0.08
    zon
    0.08
    yr
    0.08
     Peters
    0.08
    ól
    0.08
     mol
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.