© 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. 17057
    Prev
    Next
    INDEX
    Explanations

    laser beam power

    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
     Perc
    -0.10
    rollo
    -0.10
     populate
    -0.10
     doll
    -0.09
     sider
    -0.09
     rol
    -0.09
     consort
    -0.09
     expert
    -0.09
     stuffing
    -0.08
    bru
    -0.08
    POSITIVE LOGITS
     beam
    0.29
     beams
    0.27
     lasers
    0.25
     laser
    0.23
     Beam
    0.23
    beam
    0.23
     energy
    0.23
     emitter
    0.21
     energies
    0.20
    Beam
    0.20
    Activations Density 0.766%

    No Known Activations