© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27779
    Prev
    Next
    INDEX
    Explanations

    north of

    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
     proportions
    -0.11
    /reg
    -0.10
    ivors
    -0.10
    ANDOM
    -0.09
     murdering
    -0.09
    .libs
    -0.09
    hots
    -0.09
    auc
    -0.09
    sidebar
    -0.09
     tat
    -0.09
    POSITIVE LOGITS
    rie
    0.09
     Pole
    0.08
     usability
    0.08
     latitude
    0.08
    rup
    0.07
    teenth
    0.07
     peculiar
    0.07
    /cli
    0.07
     shed
    0.07
    cott
    0.07
    Activations Density 0.159%

    No Known Activations