© 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. 26405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    assen
    -0.08
     aside
    -0.08
     Tele
    -0.07
     Schneider
    -0.07
    issy
    -0.07
    ubb
    -0.07
     Aside
    -0.07
     Pang
    -0.07
     sporting
    -0.06
     tele
    -0.06
    POSITIVE LOGITS
    IDL
    0.11
    wnd
    0.11
     spur
    0.11
    abort
    0.11
     Abort
    0.10
     Coalition
    0.10
    SessionFactory
    0.10
    /package
    0.10
     </>↵
    0.10
     'č↵
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.