© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25253
    Prev
    Next
    INDEX
    Explanations

    amazement or disbelief

    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
    ubi
    -0.14
     VERY
    -0.13
     plenty
    -0.13
     obviously
    -0.12
     vengeance
    -0.11
     myster
    -0.11
    #/
    -0.11
    VERY
    -0.11
    orta
    -0.10
     certainly
    -0.10
    POSITIVE LOGITS
     actually
    0.14
     voluntarily
    0.13
     anymore
    0.12
     coincidence
    0.11
     actual
    0.11
     willingly
    0.11
     seriously
    0.10
     still
    0.10
    —that
    0.10
     finally
    0.10
    Activations Density 0.026%

    No Known Activations