© 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. 114213
    Prev
    Next
    INDEX
    Explanations

    the word "love"

    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
    anness
    -0.08
    sa
    -0.08
    Âł
    -0.08
    gings
    -0.08
     w
    -0.08
     lup
    -0.08
     SO
    -0.08
    kd
    -0.07
    unes
    -0.07
    zi
    -0.07
    POSITIVE LOGITS
    Love
    0.17
     love
    0.16
     Love
    0.16
    love
    0.16
     LOVE
    0.13
     conqu
    0.13
     loves
    0.11
     yourselves
    0.11
    /trans
    0.11
     those
    0.10
    Activations Density 0.006%

    No Known Activations