© 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. 28103
    Prev
    Next
    INDEX
    Explanations

    May invoke

    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
     Zuk
    -0.11
     captivity
    -0.10
     perfected
    -0.10
     tep
    -0.10
    ovich
    -0.10
     slog
    -0.10
    iry
    -0.10
     unm
    -0.09
    .tap
    -0.09
     Ellen
    -0.09
    POSITIVE LOGITS
     romant
    0.09
    —they
    0.08
     Morrow
    0.08
     sentimental
    0.08
    746
    0.08
    iert
    0.08
     formally
    0.07
    Âł
    0.07
    CharArray
    0.07
     error
    0.07
    Activations Density 0.005%

    No Known Activations