© 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. 31786
    Prev
    Next
    INDEX
    Explanations

    perfect for

    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
    LAG
    -0.11
    ippy
    -0.10
    zy
    -0.10
     willingly
    -0.09
     Bod
    -0.09
     lag
    -0.09
    ax
    -0.09
    Cop
    -0.09
     Mo
    -0.09
    eros
    -0.09
    POSITIVE LOGITS
     choice
    0.15
     candidate
    0.12
    choice
    0.11
     for
    0.11
     if
    0.10
     Choice
    0.10
     candidates
    0.09
     precursor
    0.09
     Pett
    0.09
     spat
    0.09
    Activations Density 0.114%

    No Known Activations