© 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. 28576
    Prev
    Next
    INDEX
    Explanations

    typically followed by descriptor

    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
     meanwhile
    -0.10
     itself
    -0.10
    erate
    -0.09
     Pra
    -0.09
     knocks
    -0.09
    bang
    -0.08
     pr
    -0.08
     ones
    -0.08
     unequal
    -0.08
     here
    -0.08
    POSITIVE LOGITS
     typically
    0.15
     often
    0.13
     oft
    0.13
     Typically
    0.13
     usually
    0.13
    semblies
    0.12
    -turned
    0.11
     Often
    0.11
    /sites
    0.11
    often
    0.11
    Activations Density 0.185%

    No Known Activations