© 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. 50347
    Prev
    Next
    INDEX
    Explanations

    correction of errors

    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
     extortion
    -0.09
    /activity
    -0.09
     Middle
    -0.09
     enthusiastically
    -0.09
     Bair
    -0.09
     enquiry
    -0.08
    /go
    -0.08
     Reese
    -0.08
     McMahon
    -0.08
     Classification
    -0.08
    POSITIVE LOGITS
     correcting
    0.40
     corrections
    0.39
     correction
    0.38
     corrected
    0.38
     Correction
    0.31
     Corrections
    0.31
     errors
    0.31
     corrective
    0.29
     Errors
    0.29
     error
    0.28
    Activations Density 1.740%

    No Known Activations