© 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. 17172
    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
     overflow
    -0.10
     Overflow
    -0.10
    plies
    -0.08
    andre
    -0.08
    sequ
    -0.08
    inke
    -0.08
     sor
    -0.08
    ëĭ
    -0.08
    aths
    -0.08
    phins
    -0.08
    POSITIVE LOGITS
     How
    0.12
    /how
    0.12
     how
    0.11
     å¦Ĥ
    0.11
    earning
    0.10
     Does
    0.10
    earn
    0.10
    how
    0.10
    How
    0.10
     earnest
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.