© 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. 49975
    Prev
    Next
    INDEX
    Explanations

    whether it is

    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
     vic
    -0.10
     stalk
    -0.10
    veis
    -0.09
    ogene
    -0.09
     Redemption
    -0.09
    enha
    -0.09
    ampp
    -0.09
    ateg
    -0.09
    urette
    -0.09
     amongst
    -0.09
    POSITIVE LOGITS
     prefer
    0.11
     preference
    0.11
     require
    0.11
     Kron
    0.10
     Prefer
    0.10
     requires
    0.10
     prefers
    0.10
     need
    0.10
     needs
    0.10
     Casual
    0.10
    Activations Density 0.009%

    No Known Activations