© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    preparation or preparing

    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
     staring
    -0.12
     penetration
    -0.11
    idl
    -0.11
     brill
    -0.10
    ilo
    -0.10
     penetrating
    -0.10
    abr
    -0.10
     jel
    -0.10
     tester
    -0.09
     flowering
    -0.09
    POSITIVE LOGITS
     preparations
    0.31
     preparation
    0.30
     preparing
    0.27
     prepar
    0.26
     prepare
    0.25
     Preparation
    0.24
     prep
    0.22
     prepares
    0.22
    Preparing
    0.22
     Prep
    0.21
    Activations Density 0.092%

    No Known Activations