© 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. 90891
    Prev
    Next
    INDEX
    Explanations

    tools and tools.ietf.org

    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
     Inspir
    -0.09
     poster
    -0.07
     card
    -0.07
     Prest
    -0.07
    omb
    -0.07
    arella
    -0.06
     framebuffer
    -0.06
     knee
    -0.06
     prest
    -0.06
     chased
    -0.06
    POSITIVE LOGITS
     tools
    0.36
     tool
    0.34
     Tools
    0.34
     Tool
    0.33
    Tool
    0.32
     toolbox
    0.32
    tool
    0.30
    Tools
    0.29
    tools
    0.29
    -tool
    0.29
    Activations Density 0.445%

    No Known Activations