© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3736
    Prev
    Next
    INDEX
    Explanations

    making a guess

    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
    erot
    -0.10
    adh
    -0.10
     Finn
    -0.09
    yz
    -0.09
     det
    -0.09
    icha
    -0.09
     mater
    -0.09
     definit
    -0.09
    -band
    -0.08
     Torch
    -0.08
    POSITIVE LOGITS
     guess
    0.22
     Guess
    0.22
     guesses
    0.21
     guessing
    0.20
    guess
    0.20
    Guess
    0.18
     guessed
    0.16
    (guess
    0.16
    _guess
    0.14
     Guest
    0.12
    Activations Density 0.006%

    No Known Activations