© 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. 91731
    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
    chen
    -0.08
     oblig
    -0.08
     scar
    -0.08
     Rider
    -0.08
     Yankee
    -0.07
     Peer
    -0.07
     Hosp
    -0.07
     Yuk
    -0.07
     minim
    -0.07
     mah
    -0.07
    POSITIVE LOGITS
     _$
    0.13
     unint
    0.11
    owski
    0.11
     `$
    0.11
    aldi
    0.11
    ssue
    0.11
     Alto
    0.11
     borders
    0.10
    Ù¾
    0.10
    zure
    0.10
    Activations Density 0.000%

    No Known Activations