© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31277
    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
     blows
    -0.10
     rec
    -0.10
     pellet
    -0.09
     dem
    -0.09
     limbs
    -0.09
    Composer
    -0.09
     ime
    -0.08
    maj
    -0.08
     MA
    -0.08
     gathering
    -0.08
    POSITIVE LOGITS
     hans
    0.09
     Pepper
    0.09
     UIF
    0.09
     epic
    0.09
    avid
    0.09
    atars
    0.09
    540
    0.08
    ubi
    0.08
    .uni
    0.08
     elbows
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.