© 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. 31306
    Prev
    Next
    INDEX
    Explanations

    light sources

    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
     generous
    -0.12
    tlement
    -0.11
     Gore
    -0.09
    isu
    -0.09
    IER
    -0.09
    ors
    -0.09
    zp
    -0.09
    ener
    -0.09
     little
    -0.09
    ted
    -0.09
    POSITIVE LOGITS
     lighting
    0.15
    bearer
    0.14
     torch
    0.14
     candles
    0.14
     bulb
    0.13
     Lighting
    0.13
    light
    0.13
     lights
    0.12
     bulbs
    0.12
     lamps
    0.12
    Activations Density 0.054%

    No Known Activations