© 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. 115089
    Prev
    Next
    INDEX
    Explanations

    reminisce about / raving about / lament / rant / wax / worry / speculated

    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
     Tavern
    -0.11
     hitch
    -0.10
    irm
    -0.10
     segmented
    -0.10
    registers
    -0.10
     stagger
    -0.10
    VISION
    -0.10
    oles
    -0.10
    moth
    -0.10
    pper
    -0.10
    POSITIVE LOGITS
     about
    0.26
     aloud
    0.18
    about
    0.17
     About
    0.16
    -about
    0.15
     ABOUT
    0.14
    _about
    0.14
    .about
    0.14
     sobre
    0.13
     openly
    0.13
    Activations Density 0.054%

    No Known Activations