© 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. 32977
    Prev
    Next
    INDEX
    Explanations

    proposal approval

    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
    /int
    -0.10
     physically
    -0.10
     Pact
    -0.10
     misd
    -0.10
     defe
    -0.10
     accessible
    -0.10
    Bookmark
    -0.10
     inaccessible
    -0.09
     ust
    -0.09
     recruited
    -0.09
    POSITIVE LOGITS
     approval
    0.42
     approvals
    0.38
     Approval
    0.36
     proposal
    0.34
     approve
    0.32
     proposals
    0.32
     approved
    0.30
    Approval
    0.30
    approval
    0.30
     approving
    0.29
    Activations Density 1.417%

    No Known Activations