© 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. 47326
    Prev
    Next
    INDEX
    Explanations

    emergency backup plans

    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
    afa
    -0.09
    ingo
    -0.09
    .ce
    -0.08
    lav
    -0.08
     gro
    -0.08
    cision
    -0.08
     Mystery
    -0.08
    aan
    -0.08
     meas
    -0.08
     cof
    -0.08
    POSITIVE LOGITS
     contingency
    0.34
     conting
    0.29
     emergencies
    0.28
     emergency
    0.26
     backup
    0.25
     Emergency
    0.22
     fallback
    0.22
    Emergency
    0.21
    ä¸ĩ
    0.21
    backup
    0.21
    Activations Density 0.701%

    No Known Activations