© 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. 46906
    Prev
    Next
    INDEX
    Explanations

    award, administered, homage, penalty, posts, interviews

    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
    ke
    -0.09
    InThe
    -0.09
    241
    -0.09
     thereof
    -0.09
     bure
    -0.09
    jem
    -0.08
    591
    -0.08
    552
    -0.08
     Lah
    -0.08
    è¿Ľè¡Į
    -0.08
    POSITIVE LOGITS
     einer
    0.12
     eines
    0.11
     Bradley
    0.11
     Mob
    0.10
    woff
    0.10
     Salv
    0.10
    toa
    0.09
     einem
    0.09
     someone
    0.09
     somebody
    0.09
    Activations Density 1.916%

    No Known Activations