© 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. 25440
    Prev
    Next
    INDEX
    Explanations

    actions following "do" variations

    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
     bio
    -0.09
     nude
    -0.09
     actividades
    -0.09
     follow
    -0.08
     activities
    -0.08
     tran
    -0.08
     followed
    -0.08
     paint
    -0.08
    nar
    -0.08
     stap
    -0.08
    POSITIVE LOGITS
     <![
    0.11
     McCabe
    0.10
     Wise
    0.10
    617
    0.10
     casualties
    0.10
     Westminster
    0.10
    roc
    0.09
     circles
    0.09
     Technologies
    0.09
     commenting
    0.09
    Activations Density 0.013%

    No Known Activations