© 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. 6832
    Prev
    Next
    INDEX
    Explanations

    specific people or roles

    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
    anka
    -0.12
    alive
    -0.11
    usch
    -0.10
    quia
    -0.10
     Trap
    -0.10
    uzz
    -0.10
    zig
    -0.09
    311
    -0.09
    aman
    -0.09
    onet
    -0.09
    POSITIVE LOGITS
     something
    0.19
     a
    0.18
     anything
    0.17
     everything
    0.16
     some
    0.16
     an
    0.15
     plenty
    0.13
     the
    0.13
     what
    0.13
     another
    0.13
    Activations Density 0.228%

    No Known Activations