© 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. 28116
    Prev
    Next
    INDEX
    Explanations

    it and

    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
     Ober
    -0.11
     Heads
    -0.10
    bek
    -0.10
    gateway
    -0.09
     Fate
    -0.09
    768
    -0.09
    ntax
    -0.09
    bk
    -0.09
     stab
    -0.08
     Gather
    -0.08
    POSITIVE LOGITS
    段
    0.10
    gee
    0.10
     tw
    0.10
     stere
    0.09
    aily
    0.09
    ived
    0.09
     precious
    0.09
    uman
    0.09
     rest
    0.09
     Cann
    0.09
    Activations Density 0.001%

    No Known Activations