© 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. 26754
    Prev
    Next
    INDEX
    Explanations

    small amounts

    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
    bags
    -0.12
     sacks
    -0.12
     churn
    -0.11
     clam
    -0.11
     nets
    -0.11
     bags
    -0.11
     shredd
    -0.11
     slam
    -0.11
     ribs
    -0.10
     hugs
    -0.10
    POSITIVE LOGITS
     drops
    0.23
     drop
    0.22
     dab
    0.21
     Drops
    0.21
     tiny
    0.20
     fingert
    0.20
     dro
    0.18
     Drop
    0.17
    -drop
    0.17
     drip
    0.17
    Activations Density 0.179%

    No Known Activations