© 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. 46472
    Prev
    Next
    INDEX
    Explanations

    he/she said or wrote

    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
     replied
    -0.16
     replies
    -0.15
     reply
    -0.15
     responded
    -0.14
    reply
    -0.14
     response
    -0.14
     respond
    -0.13
     responds
    -0.13
     Reply
    -0.12
     Dag
    -0.12
    POSITIVE LOGITS
     further
    0.25
     added
    0.23
     additionally
    0.20
     additional
    0.20
     continued
    0.20
    added
    0.17
    additional
    0.16
    -added
    0.16
     adds
    0.15
     Added
    0.15
    Activations Density 0.013%

    No Known Activations