© 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. 90096
    Prev
    Next
    INDEX
    Explanations

    prefix or suffix

    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
     unloaded
    -0.10
     Ecc
    -0.09
     Lines
    -0.09
     Christoph
    -0.09
     unload
    -0.09
    inan
    -0.09
    .Import
    -0.08
     smells
    -0.08
    gam
    -0.08
    Lines
    -0.08
    POSITIVE LOGITS
     prefix
    0.44
     prefixes
    0.37
     suffix
    0.37
     prefixed
    0.36
     Prefix
    0.31
     preceded
    0.31
     preced
    0.30
     qualifier
    0.30
    -prefix
    0.29
    prefix
    0.29
    Activations Density 1.705%

    No Known Activations