© 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. 89503
    Prev
    Next
    INDEX
    Explanations

    open or closed states

    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
     resign
    -0.10
    -article
    -0.09
     Trap
    -0.09
     Bloom
    -0.09
     recuper
    -0.09
     Designs
    -0.09
     Bios
    -0.09
     clutch
    -0.09
     unh
    -0.08
    nos
    -0.08
    POSITIVE LOGITS
     overlays
    0.11
    /start
    0.11
     prepare
    0.10
     preparing
    0.10
     overnight
    0.10
     prepares
    0.10
     nightly
    0.09
    ienda
    0.09
    oure
    0.09
    /format
    0.09
    Activations Density 0.036%

    No Known Activations