© 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. 112046
    Prev
    Next
    INDEX
    Explanations

    one and subsequent word

    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
    omat
    -0.12
     styl
    -0.10
     rake
    -0.10
     Ing
    -0.10
     Pu
    -0.09
     cent
    -0.09
     Este
    -0.09
    uxe
    -0.09
    aura
    -0.09
    ог
    -0.09
    POSITIVE LOGITS
     ones
    0.23
     indicative
    0.14
     worthy
    0.12
     worth
    0.12
    worth
    0.10
     worthwhile
    0.10
     deserving
    0.09
     fraught
    0.09
     one
    0.09
     something
    0.09
    Activations Density 0.257%

    No Known Activations