© 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. 50588
    Prev
    Next
    INDEX
    Explanations

    heard, understand, gather

    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
     probably
    -0.17
     surely
    -0.16
     obviously
    -0.16
     Probably
    -0.14
     seemingly
    -0.14
     undoubtedly
    -0.14
    probably
    -0.13
     seem
    -0.13
    Probably
    -0.13
     seems
    -0.13
    POSITIVE LOGITS
    /read
    0.10
     Partition
    0.10
    uy
    0.10
     sometimes
    0.09
    UY
    0.09
     pretty
    0.09
    ë¸
    0.09
     quite
    0.09
    ÑĪи
    0.09
     medi
    0.08
    Activations Density 0.104%

    No Known Activations