© 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. 5039
    Prev
    Next
    INDEX
    Explanations

    test, ledger, flood, applications, architectures

    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
    ashi
    -0.09
    991
    -0.09
    egra
    -0.09
    arris
    -0.09
    reau
    -0.09
     UL
    -0.09
     Dul
    -0.09
    ira
    -0.09
    abin
    -0.09
    987
    -0.09
    POSITIVE LOGITS
     they
    0.17
     each
    0.15
     Each
    0.14
     there
    0.13
     someone
    0.13
    each
    0.13
     THEY
    0.13
    Each
    0.12
     whereby
    0.12
     electrons
    0.12
    Activations Density 1.218%

    No Known Activations