© 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. 7099
    Prev
    Next
    INDEX
    Explanations

    pectoral / posterior

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     enlightenment
    -0.08
    -ticket
    -0.08
     lou
    -0.08
     pockets
    -0.08
     drip
    -0.07
     hats
    -0.07
     sesame
    -0.07
     orth
    -0.07
    ÑĥÑī
    -0.07
     merely
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.11
     Meyer
    0.11
     commod
    0.11
     PARTICULAR
    0.10
    ober
    0.10
     Commod
    0.10
    arez
    0.10
    à¹Į
    0.10
    isle
    0.10
     ||=
    0.09
    Activations Density 0.004%

    No Known Activations