© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    reverse transcription or engineering

    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
    avy
    -0.11
    acular
    -0.10
    liness
    -0.10
    edly
    -0.09
    resse
    -0.09
     Shame
    -0.09
    ular
    -0.09
    ric
    -0.09
    aken
    -0.09
    ln
    -0.08
    POSITIVE LOGITS
     engineered
    0.17
    -engine
    0.15
     engineer
    0.13
    /back
    0.13
     polarity
    0.13
     psychology
    0.11
     engineering
    0.11
     Psychology
    0.11
     Engineering
    0.11
    -direction
    0.11
    Activations Density 0.026%

    No Known Activations