© 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. 47487
    Prev
    Next
    INDEX
    Explanations

    motor vehicles and related things

    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
    uttle
    -0.09
    sm
    -0.09
    endants
    -0.08
    endant
    -0.08
    loh
    -0.08
     legisl
    -0.08
     Tanks
    -0.08
    eder
    -0.08
    etary
    -0.08
    ordinate
    -0.08
    POSITIVE LOGITS
    ized
    0.19
    bike
    0.16
    ised
    0.15
    cycl
    0.15
    ola
    0.15
    ize
    0.14
    cade
    0.14
    boat
    0.14
     neuron
    0.13
    OLA
    0.13
    Activations Density 0.029%

    No Known Activations