© 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. 91458
    Prev
    Next
    INDEX
    Explanations

    lex, Lex, Lexington

    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
    er
    -0.10
    redd
    -0.10
    834
    -0.08
    flation
    -0.08
    erator
    -0.08
    ãģ£
    -0.08
    oogle
    -0.08
     inclination
    -0.08
    lassen
    -0.08
     im
    -0.08
    POSITIVE LOGITS
     lex
    0.12
     Lex
    0.12
     lexer
    0.12
     Lexington
    0.11
     legion
    0.11
    icon
    0.10
     legitim
    0.10
    ewe
    0.10
    ibilit
    0.10
     fuzz
    0.10
    Activations Density 0.021%

    No Known Activations