© 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. 88077
    Prev
    Next
    INDEX
    Explanations

    for X years now

    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
     kim
    -0.10
    /as
    -0.10
    669
    -0.10
     transl
    -0.09
    mente
    -0.09
    oret
    -0.09
     rus
    -0.09
     Noir
    -0.09
    (SP
    -0.09
     Neville
    -0.09
    POSITIVE LOGITS
    omba
    0.10
    izo
    0.09
     cum
    0.09
     experimental
    0.09
     Shr
    0.09
    .toJSON
    0.09
     Suit
    0.09
     anchor
    0.08
    jak
    0.08
     ticking
    0.08
    Activations Density 0.011%

    No Known Activations