© 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. 25547
    Prev
    Next
    INDEX
    Explanations

    ending cessation disappearing resolved subsided faded vanished

    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
    iese
    -0.10
     unnecessarily
    -0.10
     Deg
    -0.10
    bff
    -0.09
     verbally
    -0.09
    pek
    -0.09
     Molly
    -0.09
    oup
    -0.09
     bound
    -0.09
    noch
    -0.09
    POSITIVE LOGITS
     completely
    0.13
     dissip
    0.13
     disappeared
    0.12
     resolve
    0.12
     disappear
    0.12
     disappears
    0.12
     disappearance
    0.12
     away
    0.12
     leaving
    0.11
     COMPLETE
    0.11
    Activations Density 0.037%

    No Known Activations