© 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. 6645
    Prev
    Next
    INDEX
    Explanations

    storing data on servers or devices

    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
     glob
    -0.09
    abl
    -0.09
     ali
    -0.08
     inherited
    -0.08
     stabilize
    -0.08
     myster
    -0.08
     Katherine
    -0.08
    aris
    -0.08
    leton
    -0.08
    /Set
    -0.08
    POSITIVE LOGITS
     locally
    0.16
     servers
    0.16
     cloud
    0.13
    servers
    0.13
     server
    0.12
     hosting
    0.12
     decentralized
    0.12
     local
    0.12
    -cloud
    0.12
    æľįåĬ¡åĻ¨
    0.11
    Activations Density 0.270%

    No Known Activations