© 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. 5144
    Prev
    Next
    INDEX
    Explanations

    after 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
    ys
    -0.10
    NCY
    -0.10
     McGu
    -0.10
    IFY
    -0.09
    spath
    -0.09
     unge
    -0.09
     Sense
    -0.09
     Pred
    -0.09
    emy
    -0.09
    ufe
    -0.09
    POSITIVE LOGITS
    /at
    0.14
    /in
    0.12
    /post
    0.11
    wards
    0.11
    hand
    0.10
    /out
    0.10
     Afterwards
    0.10
    ward
    0.10
    /ac
    0.10
     afterward
    0.10
    Activations Density 0.158%

    No Known Activations