© 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. 91414
    Prev
    Next
    INDEX
    Explanations

    lights and blinds

    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
    lug
    -0.10
     Ritch
    -0.09
    579
    -0.09
     intensified
    -0.09
     rut
    -0.09
    onas
    -0.08
     dungeons
    -0.08
    qu
    -0.08
    mil
    -0.08
    mun
    -0.08
    POSITIVE LOGITS
     lights
    0.42
     Lights
    0.35
    lights
    0.28
    Lights
    0.27
     lamps
    0.25
     lighting
    0.22
     blinds
    0.20
     lamp
    0.20
     Lamp
    0.20
     curtains
    0.19
    Activations Density 0.060%

    No Known Activations