© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28502
    Prev
    Next
    INDEX
    Explanations

    move past charges

    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
     herself
    -0.09
    å¥
    -0.09
     Friendly
    -0.09
     volunteers
    -0.09
    maj
    -0.09
    _yield
    -0.09
    latex
    -0.09
     verst
    -0.09
    bras
    -0.09
    abby
    -0.09
    POSITIVE LOGITS
     businessman
    0.16
     lonely
    0.15
     relaxation
    0.15
     stress
    0.15
     pent
    0.15
     Lon
    0.15
     Stress
    0.14
     businessmen
    0.14
     loneliness
    0.14
     indul
    0.14
    Activations Density 0.016%

    No Known Activations