© 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. 116824
    Prev
    Next
    INDEX
    Explanations

    X-Generator or X-UA

    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
     shar
    -0.10
    apr
    -0.10
    iders
    -0.10
     escalation
    -0.09
    ToWorld
    -0.09
     Borders
    -0.09
     Alto
    -0.09
     mini
    -0.09
     sider
    -0.09
    GREE
    -0.09
    POSITIVE LOGITS
     uniformly
    0.09
    ock
    0.09
     Front
    0.09
    ecx
    0.09
    wis
    0.09
    ek
    0.09
    olian
    0.08
    lam
    0.08
    osis
    0.08
    Wall
    0.08
    Activations Density 0.027%

    No Known Activations