© 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. 46357
    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
     ATK
    -0.10
    DeviceInfo
    -0.09
    corner
    -0.09
     Posted
    -0.09
    GBK
    -0.09
    gars
    -0.09
     surrendered
    -0.09
    FINE
    -0.09
     NONE
    -0.09
     posted
    -0.09
    POSITIVE LOGITS
    trib
    0.09
    tron
    0.09
     mon
    0.08
     waves
    0.08
     Holt
    0.08
     provision
    0.08
    bach
    0.08
     cross
    0.07
    umes
    0.07
     Wave
    0.07
    Activations Density 0.000%

    No Known Activations