© 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. 88377
    Prev
    Next
    INDEX
    Explanations

    definitive / decisive

    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
    assed
    -0.11
    MEA
    -0.08
     compart
    -0.08
     OCI
    -0.08
    leon
    -0.08
     slack
    -0.08
    asio
    -0.08
     Tig
    -0.08
    inus
    -0.07
    ris
    -0.07
    POSITIVE LOGITS
     decis
    0.19
     definitive
    0.18
     decisive
    0.17
     definit
    0.15
    ively
    0.15
     conclusive
    0.14
     proof
    0.12
     evidence
    0.12
    iveness
    0.12
     conclus
    0.12
    Activations Density 0.023%

    No Known Activations