© 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. 47904
    Prev
    Next
    INDEX
    Explanations

    sequential GIS Enterprise

    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
    /on
    -0.10
    CCC
    -0.08
    -wow
    -0.08
    /run
    -0.08
     prep
    -0.08
     cutter
    -0.08
     hoof
    -0.08
     funktion
    -0.08
    -expanded
    -0.08
     guid
    -0.08
    POSITIVE LOGITS
    adows
    0.09
    ych
    0.09
     Ebony
    0.09
    们
    0.09
    defs
    0.09
    ëĵ¤
    0.09
     clas
    0.09
    cer
    0.09
    stype
    0.09
    sy
    0.08
    Activations Density 0.059%

    No Known Activations