© 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. 113836
    Prev
    Next
    INDEX
    Explanations

    Night followed by specific 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
     daytime
    -0.13
     daylight
    -0.12
    uki
    -0.09
    headed
    -0.09
    elden
    -0.09
    iliar
    -0.09
    hardt
    -0.09
     SMA
    -0.09
    Naz
    -0.09
     summers
    -0.08
    POSITIVE LOGITS
    clubs
    0.20
    fall
    0.20
    mare
    0.19
    mar
    0.17
    mares
    0.17
    ime
    0.15
    cap
    0.14
    shade
    0.14
    crawler
    0.13
    /day
    0.13
    Activations Density 0.053%

    No Known Activations