© 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. 115925
    Prev
    Next
    INDEX
    Explanations

    Las Vegas

    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
    cil
    -0.11
    iew
    -0.10
    ering
    -0.10
     reun
    -0.09
     tod
    -0.09
    camp
    -0.09
    bite
    -0.09
    urch
    -0.09
    inde
    -0.09
    hyper
    -0.08
    POSITIVE LOGITS
     Neon
    0.09
     Jacket
    0.09
     Lid
    0.09
    ä¼
    0.09
     Dank
    0.09
     neon
    0.08
    ambi
    0.08
     Moss
    0.08
     Gunn
    0.08
     franch
    0.08
    Activations Density 0.001%

    No Known Activations