© 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. 32293
    Prev
    Next
    INDEX
    Explanations

    really going to

    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
     Beard
    -0.10
     Excellent
    -0.09
    iegel
    -0.09
    aja
    -0.09
     phot
    -0.09
     Garden
    -0.09
     unreachable
    -0.09
     Phot
    -0.09
     excellent
    -0.08
     spit
    -0.08
    POSITIVE LOGITS
     really
    0.24
     REALLY
    0.22
     truly
    0.21
     Really
    0.19
    really
    0.19
    Really
    0.17
     realmente
    0.17
     adequately
    0.17
     enough
    0.17
     realistically
    0.17
    Activations Density 0.140%

    No Known Activations