© 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. 115228
    Prev
    Next
    INDEX
    Explanations

    An variants, word beginnings

    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
     Dirt
    -0.09
     kem
    -0.09
     dau
    -0.09
     paren
    -0.08
    alem
    -0.08
    tram
    -0.08
    halt
    -0.08
     haz
    -0.08
    adge
    -0.08
     Races
    -0.08
    POSITIVE LOGITS
     AN
    0.24
     An
    0.22
    /an
    0.22
    >An
    0.20
    -An
    0.19
    .an
    0.19
    An
    0.18
    _An
    0.18
    -an
    0.17
    AN
    0.17
    Activations Density 0.096%

    No Known Activations