© 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. 3832
    Prev
    Next
    INDEX
    Explanations

    cob following variants

    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
     Monte
    -0.10
     chalk
    -0.09
    chine
    -0.09
     pog
    -0.09
     cola
    -0.08
    akin
    -0.08
     welt
    -0.08
    cribe
    -0.08
    066
    -0.08
    alive
    -0.08
    POSITIVE LOGITS
    achs
    0.08
    -Control
    0.08
     nests
    0.08
     NGX
    0.08
     Fauc
    0.08
     Rac
    0.08
    829
    0.08
     EGL
    0.08
     servic
    0.08
    raf
    0.08
    Activations Density 0.002%

    No Known Activations