© 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. 114946
    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
    -ln
    -0.11
     Airways
    -0.10
    aty
    -0.10
     misunder
    -0.10
    erson
    -0.10
     Rit
    -0.10
     Doll
    -0.10
     Rig
    -0.10
    byss
    -0.10
    iales
    -0.09
    POSITIVE LOGITS
     bed
    0.09
     Vanderbilt
    0.09
     adm
    0.09
     Bed
    0.09
     beds
    0.08
     nd
    0.08
    Bed
    0.08
    ecz
    0.08
     acqu
    0.07
     associate
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.