© 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. 50226
    Prev
    Next
    INDEX
    Explanations

    its + noun (physical or abstract)

    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
     upbringing
    -0.09
    zug
    -0.09
     imagination
    -0.09
     shaken
    -0.09
     catapult
    -0.09
     Homemade
    -0.09
     Granny
    -0.09
     Direction
    -0.08
    coop
    -0.08
     responsiveness
    -0.08
    POSITIVE LOGITS
     influence
    0.14
     presence
    0.14
     Influence
    0.13
    lef
    0.12
    presence
    0.11
     mandate
    0.11
     toll
    0.10
     payload
    0.10
     grip
    0.10
     threads
    0.10
    Activations Density 0.094%

    No Known Activations