© 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. 7884
    Prev
    Next
    INDEX
    Explanations

    us- prefix / starting / including

    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
    es
    -0.09
     counters
    -0.08
     principle
    -0.08
    bach
    -0.08
     Sac
    -0.08
     conflict
    -0.08
     surely
    -0.07
     Dou
    -0.07
     coff
    -0.07
    rops
    -0.07
    POSITIVE LOGITS
    ammen
    0.13
    htag
    0.12
    pending
    0.11
    sumer
    0.11
     Modal
    0.11
    ser
    0.11
    mods
    0.10
    queda
    0.10
    afia
    0.10
    INESS
    0.10
    Activations Density 0.062%

    No Known Activations