© 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. 88488
    Prev
    Next
    INDEX
    Explanations

    machine, Box, drivers, error

    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
     âĢ¦↵↵
    -0.08
     outfield
    -0.07
     Levine
    -0.07
    /proto
    -0.07
    ĺ认
    -0.07
     Jacqu
    -0.07
     compan
    -0.07
    -other
    -0.07
    -orders
    -0.07
    ·¸
    -0.06
    POSITIVE LOGITS
    sono
    0.13
    lek
    0.12
    cola
    0.11
    bah
    0.11
    irie
    0.11
    gary
    0.10
    LBL
    0.10
     Kushner
    0.10
     Meaning
    0.10
    ãĤĦ
    0.10
    Activations Density 0.029%

    No Known Activations