© 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. 7192
    Prev
    Next
    INDEX
    Explanations

    sudden occurrence

    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
    imonial
    -0.10
     thereafter
    -0.10
    ivos
    -0.10
     paraph
    -0.10
     bekan
    -0.09
     sentient
    -0.09
     midd
    -0.09
    ecom
    -0.09
    andel
    -0.09
    ToStr
    -0.09
    POSITIVE LOGITS
     suddenly
    0.26
     Suddenly
    0.19
     sudden
    0.17
    Suddenly
    0.16
    uddenly
    0.15
     already
    0.14
     Already
    0.13
    Already
    0.13
    already
    0.12
     voices
    0.12
    Activations Density 0.015%

    No Known Activations