© 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. 28865
    Prev
    Next
    INDEX
    Explanations

    ever since

    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
    eno
    -0.12
     Torch
    -0.11
    igos
    -0.11
    vy
    -0.10
     finally
    -0.10
    igo
    -0.10
     ea
    -0.10
    -transitional
    -0.10
     ticking
    -0.10
    zek
    -0.10
    POSITIVE LOGITS
     thereafter
    0.39
     ever
    0.29
     Ever
    0.28
     afterwards
    0.25
     afterward
    0.25
     subsequent
    0.25
    Ever
    0.23
     since
    0.23
     subsequently
    0.21
     Afterwards
    0.21
    Activations Density 0.297%

    No Known Activations