© 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. 112337
    Prev
    Next
    INDEX
    Explanations

    dark or darkness related words

    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
     Innoc
    -0.09
     personals
    -0.09
    |-
    -0.09
    quo
    -0.09
     dat
    -0.09
     mil
    -0.09
    /npm
    -0.08
     grandmother
    -0.08
    eed
    -0.08
    æį
    -0.08
    POSITIVE LOGITS
     darker
    0.16
    .Dark
    0.14
     darkest
    0.13
    /light
    0.13
    -dark
    0.13
    Dark
    0.12
     contrast
    0.12
    /black
    0.12
    dark
    0.12
     dark
    0.11
    Activations Density 0.120%

    No Known Activations