© 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. 113181
    Prev
    Next
    INDEX
    Explanations

    do what

    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
    iste
    -0.12
     Gamb
    -0.10
    gam
    -0.09
    ner
    -0.09
     gamb
    -0.09
    lig
    -0.09
     cherry
    -0.08
    ayan
    -0.08
    otel
    -0.08
    emark
    -0.08
    POSITIVE LOGITS
     necessary
    0.12
     Cly
    0.11
     Crawford
    0.10
     ple
    0.10
    bases
    0.10
    necessary
    0.10
     Pos
    0.09
     Necessary
    0.09
     pleasures
    0.09
     pos
    0.09
    Activations Density 0.007%

    No Known Activations