© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113949
    Prev
    Next
    INDEX
    Explanations

    concepts of understanding or vision

    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
     rag
    -0.09
    iente
    -0.09
    jis
    -0.09
    atas
    -0.09
     Hill
    -0.09
    vement
    -0.09
     commit
    -0.08
    USE
    -0.08
    odos
    -0.08
     Cov
    -0.08
    POSITIVE LOGITS
     vision
    0.29
     conception
    0.26
     visions
    0.25
     interpretation
    0.22
     view
    0.22
     perception
    0.21
     version
    0.21
     notion
    0.20
     interpretations
    0.20
     envision
    0.20
    Activations Density 0.254%

    No Known Activations