© 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. 26723
    Prev
    Next
    INDEX
    Explanations

    HTML/XML tags and code snippets

    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
     Eigen
    -0.10
     Schwarz
    -0.09
     supervised
    -0.09
    Eigen
    -0.09
     applaud
    -0.09
    stad
    -0.09
    infos
    -0.09
     Rubin
    -0.09
     numer
    -0.09
     Father
    -0.09
    POSITIVE LOGITS
     arm
    0.15
     Arm
    0.12
     shy
    0.09
    /arm
    0.09
    peg
    0.09
    icot
    0.09
    quet
    0.09
     cuk
    0.09
    -arm
    0.09
     eyes
    0.09
    Activations Density 0.015%

    No Known Activations