© 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. 90630
    Prev
    Next
    INDEX
    Explanations

    Some, many, most + people/opinions

    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
     oft
    -0.07
     occasion
    -0.07
    viz
    -0.07
     PROVID
    -0.07
     several
    -0.07
     behalf
    -0.07
    alin
    -0.06
    ogh
    -0.06
    lez
    -0.06
     overpower
    -0.06
    POSITIVE LOGITS
     believe
    0.24
     experts
    0.23
     commentators
    0.22
     analysts
    0.22
     argue
    0.21
     scholars
    0.21
     observers
    0.20
     critics
    0.20
     speculate
    0.19
     researchers
    0.18
    Activations Density 0.237%

    No Known Activations