© 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. 46998
    Prev
    Next
    INDEX
    Explanations

    puzzle solving

    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
     touchdown
    -0.09
     moc
    -0.09
     Volley
    -0.09
     legitim
    -0.09
     hockey
    -0.08
     skim
    -0.08
     Stat
    -0.08
     expelled
    -0.08
     multin
    -0.08
     coverage
    -0.08
    POSITIVE LOGITS
     puzzles
    0.55
     puzzle
    0.55
     Puzzle
    0.46
     solving
    0.41
     puzz
    0.40
     solved
    0.39
     solve
    0.38
     solver
    0.37
    -solving
    0.35
     Solve
    0.35
    Activations Density 0.923%

    No Known Activations