© 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. 32421
    Prev
    Next
    INDEX
    Explanations

    Brand clothing, property, attendant, House, student

    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
    umat
    -0.10
    umer
    -0.10
    ACC
    -0.10
    iminal
    -0.09
    otti
    -0.09
     Times
    -0.09
     centers
    -0.09
     Lump
    -0.08
     bed
    -0.08
    /items
    -0.08
    POSITIVE LOGITS
     replicas
    0.11
    -turned
    0.10
    -Based
    0.10
     pretended
    0.09
     liaison
    0.09
     mim
    0.09
     allied
    0.09
     wast
    0.09
    -like
    0.09
     Guth
    0.09
    Activations Density 0.008%

    No Known Activations