© 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. 6663
    Prev
    Next
    INDEX
    Explanations

    do operations

    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
    ologne
    -0.09
    igo
    -0.09
     grandchildren
    -0.09
     pepper
    -0.09
    canonical
    -0.08
    {/*
    -0.08
     sop
    -0.08
     damp
    -0.08
    iga
    -0.08
    hamster
    -0.08
    POSITIVE LOGITS
     Mou
    0.12
     rounds
    0.12
     CPR
    0.11
     Rousse
    0.11
     Rou
    0.11
     reconnaissance
    0.10
     surveys
    0.10
     laps
    0.10
     calculations
    0.10
     activities
    0.10
    Activations Density 0.110%

    No Known Activations