© 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. 3603
    Prev
    Next
    INDEX
    Explanations

    interpreting complex expressions

    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
    Negative Logits
    774
    -0.09
    <|endoftext|>
    -0.08
    \↵
    -0.08
    iley
    -0.08
    (er
    -0.08
     hass
    -0.08
     McKay
    -0.08
    itre
    -0.08
     posting
    -0.07
    isen
    -0.07
    POSITIVE LOGITS
    /config
    0.10
     Dew
    0.10
     dew
    0.10
    ete
    0.10
     INTERRU
    0.09
     interrog
    0.09
     precedence
    0.09
    Interpreter
    0.09
     sounding
    0.09
     interpre
    0.09
    Activations Density 0.004%

    No Known Activations