© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87755
    Prev
    Next
    INDEX
    Explanations

    interested or liking

    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
    Negative Logits
    usan
    -0.11
    dden
    -0.11
     receive
    -0.11
     EXPORT
    -0.11
    hoe
    -0.11
    bib
    -0.11
    blas
    -0.10
     Receive
    -0.10
     Conv
    -0.10
    -el
    -0.10
    POSITIVE LOGITS
     interest
    0.21
     interested
    0.19
     Interest
    0.18
    interested
    0.17
     Interested
    0.16
     attent
    0.16
    Interested
    0.16
     compliment
    0.14
     caring
    0.14
     liking
    0.14
    Activations Density 0.076%

    No Known Activations