© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    official sources and capacity

    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
    oftware
    -0.10
    osos
    -0.09
    meld
    -0.09
     fre
    -0.09
    lien
    -0.09
     catast
    -0.09
     marketed
    -0.09
     Patri
    -0.08
    uisse
    -0.08
     dri
    -0.08
    POSITIVE LOGITS
     bureaucracy
    0.15
     bureaucrats
    0.14
    dom
    0.14
     bureaucratic
    0.14
     corruption
    0.13
    /exec
    0.12
    /pol
    0.12
     Officials
    0.12
     Corruption
    0.12
     officials
    0.12
    Activations Density 0.155%

    No Known Activations