© 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. 50026
    Prev
    Next
    INDEX
    Explanations

    license identifiers and types

    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
    ease
    -0.09
     Sands
    -0.09
    rium
    -0.09
     Gron
    -0.08
    etch
    -0.08
     Griff
    -0.08
     âĸº
    -0.08
    ettel
    -0.08
     Deb
    -0.08
    ischen
    -0.08
    POSITIVE LOGITS
     beware
    0.11
     profitable
    0.09
    arde
    0.09
    èIJ
    0.09
     fond
    0.09
    -inspired
    0.09
     tritur
    0.09
    ugo
    0.09
     inclined
    0.08
    ands
    0.08
    Activations Density 0.001%

    No Known Activations