© 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. 16831
    Prev
    Next
    INDEX
    Explanations

    permission to use or access

    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
     Flour
    -0.09
     staffing
    -0.09
    uster
    -0.09
     resign
    -0.08
     Backbone
    -0.08
     Financing
    -0.08
     Tec
    -0.08
     Forced
    -0.08
     Fleming
    -0.08
     Funding
    -0.08
    POSITIVE LOGITS
     publish
    0.16
     reuse
    0.16
     reprint
    0.15
     usage
    0.15
     use
    0.15
     publication
    0.14
     redistribution
    0.14
     publishing
    0.14
     publicity
    0.14
     redistribute
    0.13
    Activations Density 0.039%

    No Known Activations