© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    recommendation

    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
     clue
    -0.09
     supposedly
    -0.09
     pathetic
    -0.09
     rims
    -0.08
    nesty
    -0.08
     EVER
    -0.08
     notorious
    -0.08
     ...↵
    -0.08
    igu
    -0.08
     invariably
    -0.08
    POSITIVE LOGITS
     worth
    0.19
     Recommended
    0.18
     recommend
    0.18
     recommendation
    0.18
     recommended
    0.17
     worthwhile
    0.17
     niche
    0.17
     Recommendation
    0.16
     Worth
    0.16
    Recommend
    0.16
    Activations Density 0.108%

    No Known Activations