© 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. 90088
    Prev
    Next
    INDEX
    Explanations

    candlelight, incense sticks, wax figures

    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
     transmissions
    -0.09
     coats
    -0.09
     tasting
    -0.09
     coat
    -0.09
     serialization
    -0.09
     Submit
    -0.08
     Irr
    -0.08
    Submitting
    -0.08
    pter
    -0.08
     Tanz
    -0.08
    POSITIVE LOGITS
     candles
    0.43
     candle
    0.42
     Candle
    0.38
     wax
    0.27
     Wax
    0.24
    andles
    0.23
     vot
    0.20
    wick
    0.18
     lamps
    0.18
     Wick
    0.18
    Activations Density 0.043%

    No Known Activations