© 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. 91849
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     very
    -0.12
     extremely
    -0.10
    very
    -0.10
     Very
    -0.10
    å¾
    -0.09
     Extremely
    -0.08
     being
    -0.08
    Very
    -0.08
     ultra
    -0.08
     specially
    -0.08
    POSITIVE LOGITS
     easily
    0.15
     badly
    0.15
     readily
    0.14
     Easily
    0.13
     efficiently
    0.13
     much
    0.13
    much
    0.13
     effortlessly
    0.12
     cleanly
    0.12
    zia
    0.11
    Activations Density 0.060%

    No Known Activations