© 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. 92217
    Prev
    Next
    INDEX
    Explanations

    formerly or now

    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
     exaggerated
    -0.10
     Glas
    -0.09
    å¡
    -0.09
     fixation
    -0.09
    ayne
    -0.08
     Shan
    -0.08
     Ended
    -0.08
     SIX
    -0.08
    uce
    -0.08
     Thornton
    -0.08
    POSITIVE LOGITS
     renamed
    0.56
     renaming
    0.41
     rename
    0.40
     formerly
    0.30
    rename
    0.28
     Rename
    0.28
    formerly
    0.27
    .rename
    0.24
     changed
    0.24
    Rename
    0.24
    Activations Density 1.550%

    No Known Activations