© 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. 112833
    Prev
    Next
    INDEX
    Explanations

    light emitting devices

    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
    lush
    -0.11
    pig
    -0.11
     unst
    -0.10
     Gesch
    -0.10
     coated
    -0.10
     unveiled
    -0.10
    Uvs
    -0.10
    cul
    -0.10
     forcefully
    -0.10
    composition
    -0.10
    POSITIVE LOGITS
     lights
    0.19
     blinking
    0.17
     twink
    0.16
     illumin
    0.16
     blink
    0.15
     glow
    0.15
     brightest
    0.15
     shine
    0.14
     lit
    0.14
     flick
    0.14
    Activations Density 0.171%

    No Known Activations