© 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. 32132
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and comparisons

    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
     klub
    -0.10
     flare
    -0.09
    ↵↵↵↵
    -0.09
    Kid
    -0.09
    .UR
    -0.09
    eeper
    -0.08
    Âł↵
    -0.08
     Paulo
    -0.08
    istique
    -0.08
    emb
    -0.08
    POSITIVE LOGITS
     overnight
    0.09
     incor
    0.09
     prom
    0.09
     Ivory
    0.09
     Lev
    0.09
     adc
    0.08
    registers
    0.08
     juni
    0.08
     Breed
    0.08
    puted
    0.08
    Activations Density 0.024%

    No Known Activations