© 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. 111799
    Prev
    Next
    INDEX
    Explanations

    sudden changes, switching states

    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
    ahn
    -0.10
    prit
    -0.09
    hs
    -0.08
     responsibly
    -0.08
     hoped
    -0.08
    Await
    -0.08
    ;/*
    -0.08
     awaited
    -0.08
     nud
    -0.07
     Unary
    -0.07
    POSITIVE LOGITS
     suddenly
    0.34
     sudden
    0.30
     abruptly
    0.27
     Suddenly
    0.26
     switch
    0.24
    Suddenly
    0.24
     abrupt
    0.23
     switching
    0.23
     altern
    0.23
     alternating
    0.23
    Activations Density 0.313%

    No Known Activations