© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31298
    Prev
    Next
    INDEX
    Explanations

    guess what happens

    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
    orp
    -0.07
    674
    -0.07
     misc
    -0.07
    alia
    -0.07
    âĪ
    -0.06
    Äĵ
    -0.06
     Bod
    -0.06
    aria
    -0.06
     Lal
    -0.06
    awa
    -0.06
    POSITIVE LOGITS
     guessed
    0.50
     guess
    0.46
     Guess
    0.45
     guesses
    0.40
    guess
    0.40
    Guess
    0.39
     guessing
    0.35
     unsur
    0.32
    _guess
    0.29
    (guess
    0.29
    Activations Density 0.161%

    No Known Activations