© 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. 17401
    Prev
    Next
    INDEX
    Explanations

    spark and spark plugs

    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
     cabo
    -0.14
     Doyle
    -0.13
    agem
    -0.10
    uso
    -0.10
     Peach
    -0.10
     dilig
    -0.10
    /Instruction
    -0.10
    strup
    -0.10
    hc
    -0.09
    -State
    -0.09
    POSITIVE LOGITS
     sparks
    0.18
     Sparks
    0.16
     spark
    0.15
     sparked
    0.14
     ign
    0.12
     generated
    0.12
     Spark
    0.11
     ignite
    0.11
     sparking
    0.11
    y
    0.11
    Activations Density 0.007%

    No Known Activations