© 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. 112476
    Prev
    Next
    INDEX
    Explanations

    ongoing processes

    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
     rally
    -0.09
     Kul
    -0.09
    BUG
    -0.09
     flushed
    -0.09
    =("
    -0.09
     Daw
    -0.09
     Nath
    -0.09
    fal
    -0.09
     fal
    -0.09
    jl
    -0.09
    POSITIVE LOGITS
     Meanwhile
    0.11
    oya
    0.10
     meantime
    0.10
     common
    0.10
     begun
    0.10
     Mons
    0.09
     viet
    0.09
     Siber
    0.09
     destined
    0.09
    Meanwhile
    0.08
    Activations Density 0.061%

    No Known Activations