© 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. 29756
    Prev
    Next
    INDEX
    Explanations

    arithmetic questions

    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
    aine
    -0.11
    iska
    -0.09
     whose
    -0.09
    uy
    -0.08
    rig
    -0.08
    ÑĢа
    -0.08
    uye
    -0.08
     Barn
    -0.08
     belonging
    -0.08
     &)
    -0.07
    POSITIVE LOGITS
     him
    0.15
     them
    0.12
    him
    0.12
     impecc
    0.09
     yourself
    0.09
     intoxicated
    0.09
     flushed
    0.09
     [[]
    0.09
     unmist
    0.09
    stands
    0.09
    Activations Density 0.369%

    No Known Activations