© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    reverse or reversed

    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
    uzzi
    -0.11
     incapac
    -0.10
     lump
    -0.10
     sidel
    -0.10
    quate
    -0.09
    ddf
    -0.09
     Benson
    -0.09
     duk
    -0.09
    ueur
    -0.09
     Consent
    -0.09
    POSITIVE LOGITS
     reversed
    0.65
     reversal
    0.63
     reversing
    0.60
     reverse
    0.57
     revers
    0.54
     Reverse
    0.54
     inverted
    0.52
    reverse
    0.48
     inversion
    0.47
    Reverse
    0.46
    Activations Density 0.970%

    No Known Activations