© 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. 27631
    Prev
    Next
    INDEX
    Explanations

    too small

    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
     ballo
    -0.14
    783
    -0.11
    pig
    -0.10
    OUND
    -0.10
     handic
    -0.10
     pig
    -0.10
     Gall
    -0.09
     outlier
    -0.09
     DISCLAIMER
    -0.09
     bumps
    -0.09
    POSITIVE LOGITS
     smaller
    0.13
     inadequate
    0.12
     insufficient
    0.12
     incorrect
    0.12
     wrong
    0.10
     inappropriate
    0.10
     lower
    0.10
     too
    0.09
    Incorrect
    0.09
     cheaper
    0.09
    Activations Density 0.006%

    No Known Activations