© 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. 89876
    Prev
    Next
    INDEX
    Explanations

    prefix completion

    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
    ically
    -0.11
     neighb
    -0.10
    ics
    -0.09
    etics
    -0.09
     tamp
    -0.09
    ents
    -0.09
    ationally
    -0.09
    iddy
    -0.09
    igin
    -0.09
    ently
    -0.08
    POSITIVE LOGITS
    antly
    0.10
     Vit
    0.10
     Dit
    0.10
    otic
    0.10
     welcoming
    0.10
     distinct
    0.09
    ulum
    0.09
    gem
    0.09
    Distinct
    0.09
     welcome
    0.09
    Activations Density 0.117%

    No Known Activations