© 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. 27500
    Prev
    Next
    INDEX
    Explanations

    leads to questions or realisations

    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
    Margins
    -0.10
    arda
    -0.10
    .eql
    -0.10
    intree
    -0.10
     Bau
    -0.10
    733
    -0.10
    sdk
    -0.10
    baugh
    -0.10
    heit
    -0.10
     Pere
    -0.09
    POSITIVE LOGITS
     question
    0.16
     why
    0.15
     segue
    0.13
     questions
    0.12
     another
    0.12
     ponder
    0.11
    why
    0.11
     dilemma
    0.11
     WHY
    0.11
     today
    0.10
    Activations Density 0.052%

    No Known Activations