© 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. 26441
    Prev
    Next
    INDEX
    Explanations

    opposite or reverse concepts

    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
    isky
    -0.10
    ouro
    -0.09
    503
    -0.09
    öh
    -0.09
    hoff
    -0.08
    scope
    -0.08
    azon
    -0.08
    clause
    -0.08
    Une
    -0.08
    ieren
    -0.08
    POSITIVE LOGITS
     opposite
    0.88
     reverse
    0.59
     oppos
    0.52
     converse
    0.50
     contrary
    0.47
     reversed
    0.47
     inverse
    0.47
     Conversely
    0.47
     Reverse
    0.46
    reverse
    0.43
    Activations Density 0.480%

    No Known Activations