© 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. 49163
    Prev
    Next
    INDEX
    Explanations

    exchange of data and goods

    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
     dall
    -0.10
     hovering
    -0.09
    xis
    -0.09
     cob
    -0.09
     Orb
    -0.09
     Kov
    -0.09
     escapes
    -0.08
    AV
    -0.08
     Primitive
    -0.08
     escaping
    -0.08
    POSITIVE LOGITS
    usi
    0.10
    arna
    0.10
     Eva
    0.09
     conj
    0.09
    /validation
    0.09
    enia
    0.09
     ($)
    0.09
     Chun
    0.09
     Il
    0.09
     il
    0.09
    Activations Density 0.012%

    No Known Activations