© 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. 91747
    Prev
    Next
    INDEX
    Explanations

    free software license

    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
    astos
    -0.11
     iter
    -0.09
     Rolled
    -0.09
    -na
    -0.09
    amus
    -0.09
    orial
    -0.09
    pix
    -0.09
     Laz
    -0.09
     Horn
    -0.09
     wan
    -0.09
    POSITIVE LOGITS
    è¶
    0.08
    BOOT
    0.08
     kite
    0.07
    iker
    0.07
     hook
    0.07
    âĢ¦âĢ¦↵↵
    0.07
     specifier
    0.07
     Actual
    0.07
    aleb
    0.07
    vg
    0.07
    Activations Density 0.001%

    No Known Activations