© 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. 47893
    Prev
    Next
    INDEX
    Explanations

    sounds or simple

    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
    900
    -0.10
     proportional
    -0.10
    enheim
    -0.09
     skyline
    -0.09
    611
    -0.09
    anine
    -0.09
     sublicense
    -0.09
    pear
    -0.09
    oran
    -0.09
     sectional
    -0.09
    POSITIVE LOGITS
     sounding
    0.10
     scre
    0.10
     eh
    0.10
    —and
    0.10
    efd
    0.09
     bear
    0.09
    (and
    0.09
    EX
    0.09
     huh
    0.09
     Bear
    0.08
    Activations Density 0.048%

    No Known Activations