© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16479
    Prev
    Next
    INDEX
    Explanations

    fox news

    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
     Barbie
    -0.12
     titan
    -0.11
     Lanc
    -0.11
    Titan
    -0.11
     cylinder
    -0.10
     Herc
    -0.10
     Cylinder
    -0.10
     Austrian
    -0.10
     Hernandez
    -0.10
     cylinders
    -0.10
    POSITIVE LOGITS
     fox
    0.50
     Fox
    0.45
    fox
    0.43
    Fox
    0.42
     FOX
    0.38
    FOX
    0.34
     Kits
    0.21
     tails
    0.21
     vul
    0.20
     Firefox
    0.20
    Activations Density 0.340%

    No Known Activations