© 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. 111790
    Prev
    Next
    INDEX
    Explanations

    tab or menu selection

    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
    yt
    -0.10
    bane
    -0.10
     Sab
    -0.10
     sab
    -0.09
    rie
    -0.09
    ï¼Į请
    -0.09
     incon
    -0.09
    .He
    -0.09
    liv
    -0.09
     Rag
    -0.09
    POSITIVE LOGITS
    these
    0.11
     these
    0.11
     THESE
    0.10
     everything
    0.10
     it
    0.09
     this
    0.09
    this
    0.08
     precinct
    0.08
     ÑįÑĤо
    0.08
     THEY
    0.08
    Activations Density 0.681%

    No Known Activations