© 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. 113156
    Prev
    Next
    INDEX
    Explanations

    mistakes and apologies

    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
     rede
    -0.13
     thanking
    -0.12
     Nic
    -0.11
     nic
    -0.11
     tre
    -0.11
    tre
    -0.11
     stranger
    -0.11
     deadlock
    -0.11
     inherits
    -0.11
    vale
    -0.11
    POSITIVE LOGITS
     shouldn
    0.18
     forgot
    0.16
     underestimated
    0.14
     mistakenly
    0.14
     should
    0.13
     Forgot
    0.13
     misunder
    0.13
    should
    0.13
     meant
    0.12
     wrongly
    0.12
    Activations Density 0.082%

    No Known Activations