© 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. 47484
    Prev
    Next
    INDEX
    Explanations

    error messages and exceptions

    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
     optimism
    -0.10
    byname
    -0.10
     gele
    -0.10
     anticip
    -0.10
     reservation
    -0.09
     renewed
    -0.09
     sucess
    -0.09
     anticipation
    -0.09
     affection
    -0.09
     styl
    -0.09
    POSITIVE LOGITS
     embarrassment
    0.17
     embarrassed
    0.16
     apologies
    0.15
     embarrassing
    0.14
     voyeur
    0.14
     apology
    0.14
     apologized
    0.13
     frozen
    0.13
     blackmail
    0.13
     apologize
    0.12
    Activations Density 0.044%

    No Known Activations