© 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. 116879
    Prev
    Next
    INDEX
    Explanations

    errors or error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ahl
    -0.11
     Keller
    -0.10
    etto
    -0.10
     exagger
    -0.10
     hiding
    -0.10
     weakened
    -0.10
    stalk
    -0.09
     grab
    -0.09
     bele
    -0.09
     vulnerable
    -0.09
    POSITIVE LOGITS
     error
    0.28
     Error
    0.23
     ERROR
    0.21
    error
    0.20
     errors
    0.20
     empty
    0.19
     blank
    0.19
    Error
    0.19
    -error
    0.18
     message
    0.18
    Activations Density 1.580%

    No Known Activations