© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117221
    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
     alt
    -0.08
     cultured
    -0.07
     dissent
    -0.07
    át
    -0.07
     Cree
    -0.06
    abis
    -0.06
    chet
    -0.06
     Intercept
    -0.06
     hog
    -0.06
    lug
    -0.06
    POSITIVE LOGITS
     RM
    0.12
    rible
    0.12
    rowse
    0.11
    иÑħ
    0.11
    ufe
    0.11
     Tea
    0.11
    -depth
    0.11
    _depth
    0.11
    depth
    0.11
     Hutchinson
    0.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.