© 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. 48454
    Prev
    Next
    INDEX
    Explanations

    numbers and money amounts

    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
    kre
    -0.09
    ickness
    -0.08
     conf
    -0.08
    foundation
    -0.08
    REP
    -0.08
    zman
    -0.08
    peng
    -0.08
    zik
    -0.08
    direction
    -0.08
     unpredictable
    -0.08
    POSITIVE LOGITS
    000
    0.30
    00
    0.15
     rue
    0.12
    pts
    0.11
    500
    0.11
    ooo
    0.10
    OO
    0.10
    010
    0.10
    001
    0.10
    015
    0.09
    Activations Density 0.378%

    No Known Activations