© 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. 3834
    Prev
    Next
    INDEX
    Explanations

    devoted and dedicated to

    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
     Kal
    -0.09
     Rus
    -0.09
    ignon
    -0.09
    RSA
    -0.09
     Fon
    -0.09
    eos
    -0.08
    auer
    -0.08
    TRL
    -0.08
    ALS
    -0.08
     Knox
    -0.08
    POSITIVE LOGITS
     devoted
    0.60
     dedicated
    0.48
     devote
    0.37
     dedicate
    0.36
     Dedicated
    0.35
     spent
    0.33
     reserved
    0.29
     dedic
    0.29
    spent
    0.27
     dedication
    0.24
    Activations Density 0.397%

    No Known Activations