© 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. 88483
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

    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
    oko
    -0.11
    less
    -0.08
     unser
    -0.08
     inform
    -0.08
    adel
    -0.08
     solo
    -0.08
    æij
    -0.08
     Intercept
    -0.07
     Fowler
    -0.07
    ophone
    -0.07
    POSITIVE LOGITS
     intelligence
    0.21
     Intelligence
    0.20
     inse
    0.20
    intelligence
    0.17
    /art
    0.16
     turf
    0.16
    /man
    0.14
    /engine
    0.14
     intelig
    0.13
    ity
    0.13
    Activations Density 0.112%

    No Known Activations