© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    action leading to further results

    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
     hind
    -0.11
     paving
    -0.11
    uction
    -0.11
    gew
    -0.10
    POR
    -0.10
     oneself
    -0.10
    PF
    -0.10
    trap
    -0.10
     impact
    -0.10
     Sab
    -0.10
    POSITIVE LOGITS
     marked
    0.12
     considerable
    0.11
     another
    0.10
     further
    0.10
     additional
    0.10
    ume
    0.10
    marked
    0.09
     us
    0.09
     renewed
    0.09
     thoughts
    0.09
    Activations Density 0.192%

    No Known Activations