© 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. 111998
    Prev
    Next
    INDEX
    Explanations

    transition 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
     was
    -0.26
     était
    -0.23
    was
    -0.22
     had
    -0.22
     Was
    -0.21
     wasn
    -0.21
    Was
    -0.21
    _was
    -0.20
     mattered
    -0.20
     lacked
    -0.20
    POSITIVE LOGITS
     feels
    0.18
     is
    0.17
     begins
    0.16
    —is
    0.16
     arrives
    0.15
     isn
    0.15
    —are
    0.15
     reminds
    0.14
     has
    0.14
     becomes
    0.14
    Activations Density 0.814%

    No Known Activations