© 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. 46551
    Prev
    Next
    INDEX
    Explanations

    NPR, radio, and public broadcasting

    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
    rox
    -0.11
     Ranked
    -0.10
    loff
    -0.10
     pil
    -0.09
     FORE
    -0.09
     swingers
    -0.09
     emanc
    -0.09
     Trigger
    -0.09
     MVC
    -0.09
     ped
    -0.09
    POSITIVE LOGITS
     NPR
    0.34
     PBS
    0.22
    PBS
    0.19
    pbs
    0.14
     radio
    0.14
     pledge
    0.14
    Listener
    0.13
     listener
    0.13
     listeners
    0.13
    Listeners
    0.13
    Activations Density 0.307%

    No Known Activations