© 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. 32925
    Prev
    Next
    INDEX
    Explanations

    growth and expansion

    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
     peeled
    -0.10
     academy
    -0.10
     sourcing
    -0.09
     Gran
    -0.09
     incon
    -0.08
    apl
    -0.08
     Cumberland
    -0.08
     Dor
    -0.08
    oyer
    -0.08
     building
    -0.08
    POSITIVE LOGITS
     into
    0.15
     faster
    0.14
    into
    0.13
     claws
    0.12
     differently
    0.12
     taller
    0.12
     out
    0.12
     upwards
    0.12
    bdb
    0.11
    -out
    0.11
    Activations Density 0.025%

    No Known Activations