© 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. 14351
    Prev
    Next
    INDEX
    Explanations

    urethral

    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
     weakest
    -0.08
    -as
    -0.08
    UPS
    -0.08
    itur
    -0.08
    062
    -0.08
     Establish
    -0.07
     Mais
    -0.07
    jak
    -0.07
     assort
    -0.07
    akin
    -0.07
    POSITIVE LOGITS
    rium
    0.13
     tubes
    0.13
    gia
    0.12
    elial
    0.11
     Unter
    0.10
     opening
    0.10
    emia
    0.10
     glands
    0.10
    een
    0.10
    0.10
    Activations Density 0.027%

    No Known Activations