© 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. 91245
    Prev
    Next
    INDEX
    Explanations

    concessive clauses introduced by conjunctions

    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
    itore
    -0.08
    hammer
    -0.08
     syn
    -0.07
    iou
    -0.07
    usto
    -0.07
    ...
    -0.07
    ledon
    -0.07
     Extras
    -0.07
     Yet
    -0.07
     humili
    -0.07
    POSITIVE LOGITS
     albeit
    0.14
     aside
    0.13
     despite
    0.13
     due
    0.13
    which
    0.12
     except
    0.12
     besides
    0.12
     barring
    0.12
    although
    0.12
     lest
    0.12
    Activations Density 0.276%

    No Known Activations