© 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. 89945
    Prev
    Next
    INDEX
    Explanations

    ca, caution, or caw words

    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
    ple
    -0.10
    pon
    -0.09
    jab
    -0.09
    apore
    -0.09
     recuper
    -0.08
    oste
    -0.08
    .exit
    -0.08
    pu
    -0.08
    omers
    -0.08
     Printed
    -0.08
    POSITIVE LOGITS
    iflower
    0.16
    UTION
    0.14
    ution
    0.14
    utions
    0.13
    /ca
    0.11
    ressing
    0.11
     cél
    0.11
    iazza
    0.10
    stration
    0.10
    esium
    0.10
    Activations Density 0.168%

    No Known Activations