© 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. 89298
    Prev
    Next
    INDEX
    Explanations

    flee or 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
     rested
    -0.10
     Et
    -0.09
     upsetting
    -0.09
    jem
    -0.09
     paw
    -0.09
     voter
    -0.09
    enis
    -0.09
    stopped
    -0.09
    dent
    -0.09
     lul
    -0.09
    POSITIVE LOGITS
     flee
    0.56
     fleeing
    0.54
     escape
    0.50
     fled
    0.46
     escaping
    0.42
     escapes
    0.40
     retreat
    0.40
     escaped
    0.38
     Escape
    0.38
    escape
    0.37
    Activations Density 0.195%

    No Known Activations