© 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. 116337
    Prev
    Next
    INDEX
    Explanations

    difficulty or ease

    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
     Rav
    -0.11
     rav
    -0.10
    .Embed
    -0.09
     boca
    -0.09
     Hew
    -0.09
     suppress
    -0.09
     shame
    -0.09
     dern
    -0.09
    udi
    -0.09
    BTC
    -0.09
    POSITIVE LOGITS
     difficulty
    0.54
     Difficulty
    0.48
     harder
    0.47
     hardness
    0.45
     ease
    0.45
    Difficulty
    0.45
    difficulty
    0.44
     difficulties
    0.43
     hardest
    0.42
     easier
    0.41
    Activations Density 0.378%

    No Known Activations