© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48552
    Prev
    Next
    INDEX
    Explanations

    attempts to reclaim dignity

    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
     gladly
    -0.11
     ensured
    -0.10
     prima
    -0.10
     readily
    -0.10
     considerably
    -0.10
     substantially
    -0.10
     thanks
    -0.10
    .opt
    -0.10
    abin
    -0.10
     Pais
    -0.10
    POSITIVE LOGITS
     unsuccessfully
    0.24
     futile
    0.14
     vain
    0.13
     ASAP
    0.12
     somehow
    0.12
     amidst
    0.12
     desperately
    0.12
     lest
    0.11
     amid
    0.11
     succeeding
    0.11
    Activations Density 0.196%

    No Known Activations