© 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. 25615
    Prev
    Next
    INDEX
    Explanations

    value, node, constant, assurance, technology, services

    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
     âĢ¦↵↵
    -0.07
     fringe
    -0.07
     met
    -0.07
     interf
    -0.07
     ob
    -0.07
    âĢ¦↵↵
    -0.07
     XXX
    -0.07
     others
    -0.06
     uncont
    -0.06
    âĢ¦.↵↵
    -0.06
    POSITIVE LOGITS
     Dere
    0.12
     captivating
    0.12
     catapult
    0.11
     creatively
    0.11
     adorable
    0.11
    —all
    0.11
     Shelley
    0.11
     Herrera
    0.11
    —which
    0.11
     diligently
    0.11
    Activations Density 0.001%

    No Known Activations