© 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. 29354
    Prev
    Next
    INDEX
    Explanations

    speaking or talking

    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
    annel
    -0.10
    nano
    -0.10
    anners
    -0.09
    arna
    -0.09
     hos
    -0.09
    auc
    -0.09
    kil
    -0.09
    anut
    -0.09
     Buddy
    -0.09
    )section
    -0.09
    POSITIVE LOGITS
     Speaking
    0.45
    Speaking
    0.42
     speaking
    0.36
    spe
    0.24
    -speaking
    0.24
     latter
    0.20
     which
    0.17
     speak
    0.17
     indeed
    0.16
    Talking
    0.16
    Activations Density 0.112%

    No Known Activations