© 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. 15252
    Prev
    Next
    INDEX
    Explanations

    escape

    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
    USR
    -0.09
     releg
    -0.08
     donation
    -0.08
     blush
    -0.08
     McConnell
    -0.08
     protecting
    -0.08
     Monter
    -0.08
     Exclusive
    -0.08
     Schneider
    -0.08
    .cb
    -0.08
    POSITIVE LOGITS
     escape
    0.66
     escapes
    0.56
     Escape
    0.56
     escaping
    0.53
     escaped
    0.51
    escape
    0.49
    Escape
    0.48
    escaping
    0.38
    escaped
    0.36
     escap
    0.33
    Activations Density 0.229%

    No Known Activations