© 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. 29934
    Prev
    Next
    INDEX
    Explanations

    solving puzzles and clues

    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
     Gecko
    -0.12
     Barton
    -0.10
     Viktor
    -0.10
     Talent
    -0.09
     Mol
    -0.09
    assage
    -0.09
     Roma
    -0.08
     Georg
    -0.08
    detach
    -0.08
     CMS
    -0.08
    POSITIVE LOGITS
     crossword
    0.49
     clue
    0.33
     clues
    0.32
     puzzle
    0.32
     puzzles
    0.30
     Sudoku
    0.29
     Cross
    0.28
     sudoku
    0.27
     Puzzle
    0.26
    Cross
    0.24
    Activations Density 0.275%

    No Known Activations