© 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. 33412
    Prev
    Next
    INDEX
    Explanations

    contains

    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
    aled
    -0.09
    duk
    -0.09
    yun
    -0.09
     damn
    -0.09
    tra
    -0.09
     Dam
    -0.09
     holding
    -0.09
    -and
    -0.08
    ching
    -0.08
     Elaine
    -0.08
    POSITIVE LOGITS
     elements
    0.11
     traces
    0.11
     fewer
    0.11
     enough
    0.10
     no
    0.10
     therein
    0.10
     plenty
    0.10
     spoilers
    0.10
    ä¹ī
    0.10
     lots
    0.10
    Activations Density 0.125%

    No Known Activations