© 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. 29707
    Prev
    Next
    INDEX
    Explanations

    first or before

    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
     permanently
    -0.09
     Second
    -0.09
    abe
    -0.08
    INO
    -0.08
    );;↵
    -0.08
     Next
    -0.08
     statically
    -0.08
     voluntarily
    -0.07
     throughout
    -0.07
     permanent
    -0.07
    POSITIVE LOGITS
     first
    0.63
    first
    0.50
    åħĪ
    0.50
     firstly
    0.42
     FIRST
    0.42
     beforehand
    0.41
     primero
    0.38
     before
    0.36
    First
    0.36
    -first
    0.36
    Activations Density 0.983%

    No Known Activations