© 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. 90932
    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
     FIN
    -0.09
    crow
    -0.08
    [/
    -0.08
    702
    -0.07
     unre
    -0.07
     burge
    -0.07
     Carlson
    -0.07
     comprehension
    -0.07
    cdc
    -0.07
     reaching
    -0.07
    POSITIVE LOGITS
     selective
    0.10
     accumulating
    0.10
     Tot
    0.10
     sip
    0.10
    á»iji
    0.10
     ambit
    0.10
    accumulate
    0.10
    amina
    0.10
    VIC
    0.10
    irk
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.