© 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. 92126
    Prev
    Next
    INDEX
    Explanations

    . followed by word

    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
     protagonist
    -0.06
     он
    -0.06
     Bol
    -0.05
    255
    -0.05
    argent
    -0.05
    ellan
    -0.05
    396
    -0.05
    osti
    -0.05
    ingle
    -0.05
    enty
    -0.05
    POSITIVE LOGITS
    Č↵
    0.13
     nud
    0.12
    ypad
    0.12
    pora
    0.12
    .Fat
    0.12
     discrepan
    0.12
     noticing
    0.12
    /stretch
    0.12
    /sn
    0.11
    conj
    0.11
    Activations Density 0.155%

    No Known Activations