© 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. 14954
    Prev
    Next
    INDEX
    Explanations

    code definition keywords

    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
     Woodward
    -0.10
     Brigham
    -0.08
     Unknown
    -0.08
     Cla
    -0.08
    pson
    -0.08
    uset
    -0.08
     systemic
    -0.08
     skewed
    -0.07
     whisper
    -0.07
     hammer
    -0.07
    POSITIVE LOGITS
     respective
    0.11
     Méd
    0.10
     Tale
    0.10
     entirety
    0.09
     swiftly
    0.09
     Nev
    0.09
    312
    0.09
    uz
    0.09
     Sark
    0.09
     somebody
    0.09
    Activations Density 0.005%

    No Known Activations