© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    its own

    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
     Berger
    -0.09
    -strong
    -0.08
     Vet
    -0.08
     Charter
    -0.08
     Alla
    -0.08
     eg
    -0.08
     Bott
    -0.07
     mismatch
    -0.07
     Nin
    -0.07
     solitary
    -0.07
    POSITIVE LOGITS
     tier
    0.11
     benefits
    0.11
     pros
    0.11
     intens
    0.11
    oce
    0.11
     monthly
    0.10
     advantages
    0.10
     perks
    0.10
     ramifications
    0.10
     requis
    0.10
    Activations Density 0.001%

    No Known Activations