© 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. 111675
    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
    su
    -0.12
     SAX
    -0.11
     commend
    -0.11
     philanth
    -0.11
    abo
    -0.11
     hand
    -0.11
     subcontract
    -0.11
     Blick
    -0.11
     commissions
    -0.11
    vos
    -0.11
    POSITIVE LOGITS
     exploring
    0.10
     exploration
    0.08
     expr
    0.08
     bored
    0.07
     unre
    0.07
     Exploration
    0.06
     unin
    0.06
     timid
    0.06
    Copyright
    0.06
     enjoying
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.