© 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. 26665
    Prev
    Next
    INDEX
    Explanations

    `.css`, `vim`, `cells`, `:`

    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
     Tier
    -0.10
    Tier
    -0.10
     Crest
    -0.09
     Verd
    -0.09
     sworn
    -0.09
    erver
    -0.09
    uten
    -0.09
     Apparel
    -0.08
     Tee
    -0.08
     tier
    -0.08
    POSITIVE LOGITS
     hybrids
    0.10
    ital
    0.10
     Sherman
    0.10
     Cri
    0.09
     pont
    0.09
     hybrid
    0.09
     oc
    0.09
     Lager
    0.09
    lear
    0.09
     Cruc
    0.09
    Activations Density 0.001%

    No Known Activations