© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    license information

    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
     copyright
    -0.11
     rights
    -0.10
     ownership
    -0.10
     copyrights
    -0.10
     Rights
    -0.10
     monopoly
    -0.10
     COPYRIGHT
    -0.10
    Ownership
    -0.10
     Ownership
    -0.09
    -owned
    -0.09
    POSITIVE LOGITS
    wend
    0.10
    revision
    0.10
    Contact
    0.10
     challeng
    0.09
    contact
    0.09
    AVIS
    0.09
     contact
    0.09
    ocr
    0.09
    OLDER
    0.09
    ocal
    0.08
    Activations Density 0.193%

    No Known Activations