© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25702
    Prev
    Next
    INDEX
    Explanations

    long duration or extent

    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
    ered
    -0.09
     cla
    -0.09
    apsed
    -0.08
    ema
    -0.08
     Emin
    -0.08
    werk
    -0.08
     longest
    -0.08
     realization
    -0.08
    -long
    -0.08
     repl
    -0.08
    POSITIVE LOGITS
    heck
    0.11
    ibo
    0.11
    Nach
    0.10
    ITCH
    0.10
    ifu
    0.09
     Walk
    0.09
     bola
    0.09
     Naomi
    0.09
     Johann
    0.09
    cdn
    0.09
    Activations Density 0.007%

    No Known Activations