© 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. 46252
    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
     McA
    -0.09
    &s
    -0.08
     NSS
    -0.08
     Glad
    -0.08
     sovereignty
    -0.08
     terms
    -0.08
     plotting
    -0.08
    .dup
    -0.08
     Coll
    -0.08
     Dep
    -0.08
    POSITIVE LOGITS
     IMPLIED
    0.11
    /lists
    0.10
     hydr
    0.10
    ombre
    0.10
    hon
    0.10
     honoured
    0.09
     lick
    0.09
     bras
    0.09
     jer
    0.09
     todd
    0.09
    Activations Density 0.000%

    No Known Activations