© 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. 25545
    Prev
    Next
    INDEX
    Explanations

    linked to step

    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
    uede
    -0.11
     deficits
    -0.10
    holm
    -0.10
     cors
    -0.10
    imuth
    -0.10
     Sok
    -0.10
     Dt
    -0.10
    aggio
    -0.10
    onna
    -0.09
     robber
    -0.09
    POSITIVE LOGITS
     ‘
    0.09
     Skeleton
    0.09
     institutional
    0.08
     skeleton
    0.08
     “
    0.08
     Payne
    0.07
    uctions
    0.07
     walker
    0.07
     comparable
    0.07
    mun
    0.07
    Activations Density 0.001%

    No Known Activations