© 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. 7573
    Prev
    Next
    INDEX
    Explanations

    conjunctions "and"/"or" followed by nouns

    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
    -,
    -0.10
    lich
    -0.07
    unately
    -0.07
    uth
    -0.06
    -${
    -0.06
    otre
    -0.06
     richtig
    -0.06
     bastante
    -0.06
    quis
    -0.06
    ason
    -0.06
    POSITIVE LOGITS
    /or
    0.13
    lash
    0.10
     wh
    0.10
    phet
    0.10
    بر
    0.10
    .Tasks
    0.10
    ...↵↵↵↵
    0.09
    andre
    0.09
     MOV
    0.09
     PURE
    0.09
    Activations Density 0.950%

    No Known Activations