© 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. 29949
    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
    sd
    -0.09
     Gregg
    -0.08
     ...↵
    -0.07
    arium
    -0.07
    jes
    -0.07
     Goldberg
    -0.07
     NEO
    -0.07
     Mime
    -0.07
     vein
    -0.07
    pac
    -0.06
    POSITIVE LOGITS
    000
    0.13
    shadow
    0.11
    itra
    0.11
     wholesale
    0.11
     but
    0.11
     though
    0.11
    vol
    0.11
     Lov
    0.10
    olle
    0.10
     she
    0.10
    Activations Density 0.000%

    No Known Activations