© 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. 17468
    Prev
    Next
    INDEX
    Explanations

    URL or source

    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
    iki
    -0.11
     wre
    -0.10
     favors
    -0.10
    .$.
    -0.10
    -Line
    -0.10
     Simmons
    -0.10
    ÙĦا
    -0.09
    ibbon
    -0.09
     citizenship
    -0.09
    esa
    -0.09
    POSITIVE LOGITS
     mal
    0.10
     vac
    0.09
    pto
    0.08
     episode
    0.08
     sophomore
    0.08
     craw
    0.07
     Vas
    0.07
    aza
    0.07
    imest
    0.07
    åįĪ
    0.07
    Activations Density 0.001%

    No Known Activations