© 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. 112727
    Prev
    Next
    INDEX
    Explanations

    missed or neglected information

    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
    kest
    -0.10
     Reject
    -0.09
     Ti
    -0.09
     overshadow
    -0.09
    Suppress
    -0.09
     sel
    -0.09
     rejects
    -0.09
    ador
    -0.08
    haus
    -0.08
     Omar
    -0.08
    POSITIVE LOGITS
     missed
    0.16
     miss
    0.15
     misses
    0.14
     notice
    0.14
     unaware
    0.13
     dangerously
    0.12
     neglect
    0.11
     realize
    0.11
    cko
    0.11
     neglected
    0.10
    Activations Density 0.029%

    No Known Activations