© 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. 30730
    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
     extreme
    -0.10
     Extreme
    -0.10
     extremes
    -0.08
    Extreme
    -0.08
     bead
    -0.07
    227
    -0.07
     Mercy
    -0.07
     exposing
    -0.07
    orz
    -0.07
     Rounded
    -0.07
    POSITIVE LOGITS
     Good
    0.14
     good
    0.13
    Good
    0.13
    good
    0.12
    _good
    0.11
     ench
    0.11
     GOOD
    0.11
     Pey
    0.11
     Bail
    0.10
     rub
    0.10
    Activations Density 0.002%

    No Known Activations