© 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. 29172
    Prev
    Next
    INDEX
    Explanations

    compilation error

    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
    olon
    -0.10
     impuls
    -0.10
     Dough
    -0.09
     finger
    -0.09
     shar
    -0.09
    neau
    -0.09
     Tester
    -0.09
    bench
    -0.08
    finger
    -0.08
     advent
    -0.08
    POSITIVE LOGITS
     provinc
    0.10
    abee
    0.10
    996
    0.10
    .--
    0.09
     Shield
    0.09
    é¦
    0.09
    trash
    0.09
    unga
    0.09
    amo
    0.09
    Shield
    0.09
    Activations Density 0.001%

    No Known Activations