© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    immediately, already, or right away

    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
    gli
    -0.11
    .cgi
    -0.10
     sudden
    -0.10
     further
    -0.10
    ipt
    -0.10
     finally
    -0.10
     Rally
    -0.10
     CALLBACK
    -0.10
     Gale
    -0.10
    udiant
    -0.10
    POSITIVE LOGITS
     knew
    0.12
     already
    0.10
     Already
    0.10
     {*
    0.09
    Immediately
    0.09
    iram
    0.09
    Already
    0.09
     destined
    0.09
     regret
    0.09
     recognized
    0.09
    Activations Density 0.074%

    No Known Activations