© 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. 30051
    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
     scrim
    -0.14
    utow
    -0.13
     LUA
    -0.12
    ulong
    -0.12
     wur
    -0.12
     consect
    -0.11
    Manifest
    -0.11
    [/
    -0.11
    xico
    -0.11
    /md
    -0.11
    POSITIVE LOGITS
     Olson
    0.08
     dot
    0.08
     Clifford
    0.07
     list
    0.07
     div
    0.07
     unsafe
    0.07
    BG
    0.07
     Vi
    0.06
     Ness
    0.06
     rank
    0.06
    Activations Density 0.000%

    No Known Activations