© 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. 115863
    Prev
    Next
    INDEX
    Explanations

    ak, aff, und, alk, un, ag, ak

    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
     unearth
    -0.10
    strand
    -0.10
     patron
    -0.09
     uncon
    -0.09
     CLOCK
    -0.09
    ynos
    -0.08
     AIS
    -0.08
     coincidence
    -0.08
     mis
    -0.08
    infra
    -0.08
    POSITIVE LOGITS
    uble
    0.09
    orro
    0.09
     Artikel
    0.09
     Maid
    0.08
    izzle
    0.08
     shr
    0.08
     flock
    0.08
    alar
    0.08
     Giz
    0.08
    iforn
    0.08
    Activations Density 0.155%

    No Known Activations