© 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. 14311
    Prev
    Next
    INDEX
    Explanations

    methods, glands, facilities, treatments, techniques, siblings, towers, patients

    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
     duo
    -0.15
     both
    -0.15
     twins
    -0.15
     Both
    -0.14
    Both
    -0.13
    both
    -0.13
     BOTH
    -0.12
     beide
    -0.12
    _both
    -0.11
    :both
    -0.11
    POSITIVE LOGITS
     abre
    0.15
    -quarters
    0.15
     consec
    0.14
     consecutive
    0.14
     plus
    0.13
    -four
    0.13
    teenth
    0.13
    rd
    0.13
     simultaneously
    0.13
     amigos
    0.12
    Activations Density 0.888%

    No Known Activations