© 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. 115787
    Prev
    Next
    INDEX
    Explanations

    scoring or rating

    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
    izon
    -0.10
     reconciliation
    -0.10
     reconc
    -0.09
    ray
    -0.08
     millionaire
    -0.08
     Cob
    -0.08
     Omn
    -0.08
     Peek
    -0.07
    amaha
    -0.07
     Fortune
    -0.07
    POSITIVE LOGITS
     rating
    0.62
     score
    0.55
     ratings
    0.55
     rated
    0.53
     scores
    0.52
     scored
    0.51
     Rating
    0.51
     scoring
    0.51
     Ratings
    0.48
     Score
    0.46
    Activations Density 0.706%

    No Known Activations