© 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. 50113
    Prev
    Next
    INDEX
    Explanations

    speakers, artists, groups

    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
    unts
    -0.12
     domic
    -0.12
    uteur
    -0.11
     domicile
    -0.11
     socialism
    -0.10
     communism
    -0.10
    bred
    -0.10
     synagogue
    -0.10
     Ages
    -0.10
    itar
    -0.10
    POSITIVE LOGITS
     humans
    0.22
     youngsters
    0.17
     adults
    0.17
     Canadians
    0.17
     professionals
    0.16
     Americans
    0.16
     Christians
    0.16
     enthusiasts
    0.16
     young
    0.15
     Humans
    0.15
    Activations Density 0.120%

    No Known Activations