© 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. 28812
    Prev
    Next
    INDEX
    Explanations

    rivets or rivers

    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
     blankets
    -0.08
    -pro
    -0.08
     closing
    -0.07
     blanket
    -0.07
     Landing
    -0.07
    lie
    -0.07
     exclusive
    -0.07
    Sphere
    -0.07
     falling
    -0.07
    ative
    -0.07
    POSITIVE LOGITS
    -mounted
    0.13
    ero
    0.12
    unto
    0.12
    ledon
    0.12
    eyed
    0.11
    -eyed
    0.11
     Wenger
    0.11
     Pron
    0.11
    erland
    0.11
    illance
    0.11
    Activations Density 0.003%

    No Known Activations