© 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. 116361
    Prev
    Next
    INDEX
    Explanations

    features and functionality

    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
     clicked
    -0.12
    unga
    -0.11
    lore
    -0.11
     Unauthorized
    -0.10
     enthus
    -0.10
     pity
    -0.10
    -using
    -0.10
     circa
    -0.10
    enaire
    -0.09
     Blues
    -0.09
    POSITIVE LOGITS
     options
    0.24
     option
    0.24
     functionality
    0.21
     capabilities
    0.21
     capability
    0.18
     support
    0.18
     features
    0.18
     functionalities
    0.17
     mode
    0.17
     feature
    0.16
    Activations Density 0.656%

    No Known Activations