© 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. 50048
    Prev
    Next
    INDEX
    Explanations

    the art of

    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
     ambitions
    -0.11
    antd
    -0.11
    den
    -0.10
    vor
    -0.09
    reib
    -0.09
    uthor
    -0.09
    eper
    -0.09
     dni
    -0.09
     breadth
    -0.09
    /node
    -0.09
    POSITIVE LOGITS
     perfected
    0.36
     mastered
    0.30
     art
    0.23
     refined
    0.22
     skill
    0.21
     mastery
    0.21
     perfection
    0.19
     technique
    0.19
     craft
    0.19
     mastering
    0.19
    Activations Density 0.060%

    No Known Activations