© 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. 25459
    Prev
    Next
    INDEX
    Explanations

    Clough, Clathurellinae, Clackmannanshire, Clouston, clapper bridge

    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
     Strap
    -0.10
     wholes
    -0.10
     plung
    -0.09
     conclus
    -0.08
     bw
    -0.08
    /end
    -0.08
     clones
    -0.08
    ippy
    -0.08
     Lockheed
    -0.08
     blink
    -0.08
    POSITIVE LOGITS
     bargain
    0.11
     baj
    0.10
     benchmark
    0.10
     coff
    0.09
     mour
    0.09
     bench
    0.08
     Bundy
    0.08
     gradu
    0.08
    prompt
    0.08
    benchmark
    0.08
    Activations Density 0.280%

    No Known Activations