© 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. 114191
    Prev
    Next
    INDEX
    Explanations

    and concepts or genres

    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
     characters
    -0.21
    characters
    -0.17
     Characters
    -0.15
    Characters
    -0.14
    _characters
    -0.12
     character
    -0.12
     characterize
    -0.12
    .characters
    -0.12
     chair
    -0.11
     characterized
    -0.11
    POSITIVE LOGITS
    opi
    0.10
    ibil
    0.10
     grandchildren
    0.09
    .isDefined
    0.09
     Dialog
    0.09
    ìĹ´
    0.09
     voc
    0.09
     Mellon
    0.09
    .fig
    0.09
    istica
    0.09
    Activations Density 0.120%

    No Known Activations