© 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. 30795
    Prev
    Next
    INDEX
    Explanations

    soulmate, pack, bond, vectors, settlement, mark

    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
    aby
    -0.11
     backstage
    -0.10
    agar
    -0.10
    ude
    -0.10
     habit
    -0.10
    ilden
    -0.10
     abstraction
    -0.09
     audition
    -0.09
     habits
    -0.09
     routines
    -0.09
    POSITIVE LOGITS
     unmistak
    0.11
     mate
    0.11
    rix
    0.10
     Skip
    0.10
     mates
    0.10
     bond
    0.10
    bond
    0.09
     null
    0.09
     recognised
    0.09
     prospect
    0.09
    Activations Density 0.012%

    No Known Activations