© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    find out

    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
    utsch
    -0.10
     Kale
    -0.08
     Sha
    -0.08
     Fach
    -0.08
    asse
    -0.08
     ry
    -0.08
     Yin
    -0.08
    ksen
    -0.08
    ipy
    -0.08
    EMENT
    -0.08
    POSITIVE LOGITS
     find
    0.23
     FIND
    0.23
     discover
    0.22
    find
    0.22
     Find
    0.22
    Find
    0.21
     finding
    0.21
     finds
    0.21
     Discover
    0.21
    -find
    0.21
    Activations Density 0.158%

    No Known Activations