© 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. 50276
    Prev
    Next
    INDEX
    Explanations

    sounds and sensory perception

    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
    jal
    -0.11
     baptized
    -0.10
     Williamson
    -0.10
    Cre
    -0.09
    asa
    -0.09
     Tud
    -0.09
    -0.09
    ogan
    -0.09
    igner
    -0.09
    prit
    -0.09
    POSITIVE LOGITS
     rain
    0.11
     sight
    0.10
     cic
    0.10
     laughter
    0.09
     sque
    0.09
     Heard
    0.09
     ticking
    0.09
     sound
    0.09
     reson
    0.09
     waves
    0.08
    Activations Density 0.005%

    No Known Activations