© 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. 33807
    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
     decorations
    -0.10
    endo
    -0.10
    olith
    -0.10
     unthinkable
    -0.10
     surprises
    -0.09
    atr
    -0.09
     PY
    -0.09
    aea
    -0.09
    ena
    -0.09
     lifes
    -0.09
    POSITIVE LOGITS
     guilty
    0.09
    /un
    0.09
     sok
    0.09
    -feira
    0.08
    nos
    0.08
    eve
    0.08
     Hogan
    0.08
    -Un
    0.08
    amedi
    0.08
     involved
    0.07
    Activations Density 0.000%

    No Known Activations