© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115162
    Prev
    Next
    INDEX
    Explanations

    something like

    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
     Pac
    -0.10
    wend
    -0.09
     Pis
    -0.09
     <↵
    -0.09
    uml
    -0.08
    een
    -0.08
    071
    -0.08
    irt
    -0.08
    IVEN
    -0.08
    /terms
    -0.08
    POSITIVE LOGITS
     so
    0.12
     like
    0.11
     profess
    0.10
    ellan
    0.10
    ania
    0.09
     Tango
    0.09
    /company
    0.09
     akin
    0.09
    lick
    0.09
     conce
    0.09
    Activations Density 0.048%

    No Known Activations