© 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. 17301
    Prev
    Next
    INDEX
    Explanations

    scientific and technical titles

    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
    ...
    -0.11
    --
    -0.10
    esser
    -0.10
     "
    -0.10
     "...
    -0.09
    "
    -0.09
     ""
    -0.09
    'Neill
    -0.09
     '
    -0.09
    'n
    -0.08
    POSITIVE LOGITS
    ——
    0.14
    ————
    0.13
     :</
    0.13
     meno
    0.12
     roman
    0.12
     :↵↵↵↵
    0.12
     :↵↵
    0.12
    ’T
    0.12
    ’)
    0.12
     .↵↵
    0.12
    Activations Density 0.030%

    No Known Activations