© 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. 32867
    Prev
    Next
    INDEX
    Explanations

    copyright license Version

    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
     blending
    -0.07
    Ñıд
    -0.07
     undercut
    -0.07
     Introduced
    -0.07
    inha
    -0.07
    pur
    -0.07
    isk
    -0.06
     chill
    -0.06
    orda
    -0.06
    591
    -0.06
    POSITIVE LOGITS
     Haram
    0.11
     elective
    0.11
    edin
    0.11
    536
    0.11
     dou
    0.11
     costing
    0.11
     magazines
    0.11
    aran
    0.11
    ';↵↵↵↵
    0.10
    tram
    0.10
    Activations Density 0.001%

    No Known Activations