© 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. 30891
    Prev
    Next
    INDEX
    Explanations

    right now or right away

    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
     damned
    -0.08
    oras
    -0.08
    oken
    -0.08
    adin
    -0.08
    OTO
    -0.07
     pseud
    -0.07
    biased
    -0.07
    uelle
    -0.07
     yak
    -0.07
    itar
    -0.07
    POSITIVE LOGITS
    away
    0.11
    -fetch
    0.11
     smack
    0.11
     Swal
    0.10
     Flying
    0.10
     away
    0.10
    quier
    0.10
    fully
    0.10
     opposite
    0.10
     flew
    0.10
    Activations Density 0.032%

    No Known Activations