© 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. 49157
    Prev
    Next
    INDEX
    Explanations

    services and accounts

    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
    inand
    -0.11
    444
    -0.10
     arriv
    -0.10
     arrival
    -0.10
     indeed
    -0.10
    iniz
    -0.10
     virtue
    -0.10
    Fatal
    -0.10
    rides
    -0.10
     Virt
    -0.09
    POSITIVE LOGITS
     Offline
    0.09
     Ignore
    0.08
     Wilhelm
    0.08
     lifted
    0.08
     ohne
    0.08
     shar
    0.08
    -Smith
    0.08
     Invite
    0.08
     secrets
    0.08
     without
    0.08
    Activations Density 0.006%

    No Known Activations