© 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. 27996
    Prev
    Next
    INDEX
    Explanations

    disorder or mess

    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
     Hick
    -0.09
    /app
    -0.09
     paired
    -0.09
    Contents
    -0.09
    ledge
    -0.09
    elts
    -0.08
     juxtap
    -0.08
     plata
    -0.08
     contents
    -0.08
    Lik
    -0.08
    POSITIVE LOGITS
     fray
    0.13
     haze
    0.12
     layers
    0.11
     piles
    0.11
     heap
    0.11
    886
    0.11
     clutter
    0.10
     obstruct
    0.10
     Stevenson
    0.10
    ouns
    0.10
    Activations Density 0.105%

    No Known Activations