© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    comments or technical documentation

    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
     Scarlet
    -0.07
     Gould
    -0.07
    ↵
    -0.07
     Gay
    -0.07
     Jes
    -0.06
     neat
    -0.06
     impe
    -0.06
     Swipe
    -0.06
     kep
    -0.06
     ruin
    -0.06
    POSITIVE LOGITS
    FAQ
    0.13
     Related
    0.13
    istas
    0.12
    Related
    0.12
    Others
    0.12
    *)↵↵
    0.12
     Miscellaneous
    0.12
     Frequently
    0.11
    Datas
    0.11
     absorbs
    0.11
    Activations Density 0.102%

    No Known Activations