© 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. 17576
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
     Zuk
    -0.11
     comer
    -0.10
    ugar
    -0.10
    thinkable
    -0.10
     decisive
    -0.10
    &R
    -0.10
    OBJ
    -0.10
    Bold
    -0.10
    -store
    -0.10
     Short
    -0.09
    POSITIVE LOGITS
     zig
    0.09
    akin
    0.08
     Inquiry
    0.08
     Stam
    0.08
     Floyd
    0.08
     Invest
    0.08
     Tos
    0.07
     agony
    0.07
    /pro
    0.07
    owers
    0.07
    Activations Density 0.087%

    No Known Activations