© 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. 113909
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
     Wid
    -0.06
    olf
    -0.06
    azzi
    -0.06
    arding
    -0.06
     fir
    -0.06
     physic
    -0.06
    quia
    -0.06
    jon
    -0.06
    std
    -0.06
     Wes
    -0.06
    POSITIVE LOGITS
     NumberOf
    0.11
    ()._
    0.11
    /pi
    0.11
     snatch
    0.11
     Tradable
    0.11
    ermalink
    0.11
    .jp
    0.11
     rus
    0.11
     Rosenstein
    0.10
     baptized
    0.10
    Activations Density 0.019%

    No Known Activations