© 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. 30940
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    urat
    -0.11
    oder
    -0.10
    lah
    -0.10
     uneasy
    -0.10
     certify
    -0.10
     Bair
    -0.09
     joys
    -0.09
     happiest
    -0.09
    GOR
    -0.09
     tritur
    -0.09
    POSITIVE LOGITS
     part
    0.20
     standalone
    0.16
     an
    0.16
     means
    0.15
     a
    0.15
     alternative
    0.15
     replacements
    0.14
     tool
    0.13
     entertainment
    0.13
     supplemental
    0.12
    Activations Density 0.306%

    No Known Activations