© 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. 47937
    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
    Routine
    -0.12
     automáticamente
    -0.11
     hinter
    -0.11
    routine
    -0.11
    wyn
    -0.11
     timetable
    -0.11
     duk
    -0.11
     RD
    -0.10
    iko
    -0.10
    wow
    -0.10
    POSITIVE LOGITS
     sup
    0.08
    yme
    0.08
     Coh
    0.08
    anse
    0.07
     covert
    0.07
     Gst
    0.07
     Bind
    0.07
     schem
    0.07
    UDA
    0.07
     Beat
    0.07
    Activations Density 0.000%

    No Known Activations