© 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. 34090
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

    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
     Excellent
    -0.14
    Excellent
    -0.13
     excellent
    -0.13
     ugl
    -0.12
     excelente
    -0.12
     unpleasant
    -0.11
     magnificent
    -0.11
    CG
    -0.11
     excellence
    -0.11
     sublime
    -0.11
    POSITIVE LOGITS
    -looking
    0.13
    ly
    0.10
    /simple
    0.10
    /use
    0.10
     albeit
    0.10
    maal
    0.10
    eee
    0.09
    fully
    0.09
    lei
    0.09
    /slick
    0.09
    Activations Density 0.203%

    No Known Activations