© 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. 112780
    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
     desc
    -0.08
    vat
    -0.08
     frustrations
    -0.08
     asc
    -0.07
     +-
    -0.07
     intact
    -0.07
     Active
    -0.07
     holds
    -0.07
     accessible
    -0.07
     neg
    -0.07
    POSITIVE LOGITS
    hire
    0.11
    andas
    0.10
    ckt
    0.10
    /window
    0.10
    mpp
    0.10
    /drivers
    0.10
     Resp
    0.10
    uele
    0.10
     Kre
    0.10
    orgot
    0.10
    Activations Density 0.000%

    No Known Activations