© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46709
    Prev
    Next
    INDEX
    Explanations

    ownership and copyright licensing

    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
     courtesy
    -0.11
    cour
    -0.11
    bia
    -0.10
    447
    -0.10
     Courtesy
    -0.10
     beg
    -0.09
     plagued
    -0.09
     заг
    -0.09
    enha
    -0.09
     caution
    -0.09
    POSITIVE LOGITS
     ownership
    0.20
     Ownership
    0.16
     owned
    0.16
     copyrighted
    0.15
     copyright
    0.15
     Copyright
    0.14
    Ownership
    0.14
     owns
    0.13
     borrowed
    0.13
     trademark
    0.13
    Activations Density 0.040%

    No Known Activations