© 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. 28444
    Prev
    Next
    INDEX
    Explanations

    lists of things

    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
     trous
    -0.11
     twin
    -0.11
     Rac
    -0.11
    /category
    -0.11
     zad
    -0.10
    Bracket
    -0.10
    tal
    -0.10
    arker
    -0.10
    arnation
    -0.10
     ken
    -0.10
    POSITIVE LOGITS
     alike
    0.26
     apl
    0.12
     etc
    0.11
     thereof
    0.10
     gal
    0.09
    ajes
    0.08
    pies
    0.08
    -turned
    0.07
     assorted
    0.07
    ides
    0.07
    Activations Density 0.502%

    No Known Activations