© 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. 30924
    Prev
    Next
    INDEX
    Explanations

    champion of

    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
    uate
    -0.10
    omb
    -0.08
    casting
    -0.08
    ual
    -0.08
    vik
    -0.08
    bite
    -0.07
    .foundation
    -0.07
    vang
    -0.07
    ward
    -0.07
    chie
    -0.07
    POSITIVE LOGITS
    rous
    0.15
    -elect
    0.14
    agne
    0.14
    nat
    0.13
     boxer
    0.12
    ships
    0.12
     wrestler
    0.12
    etre
    0.12
    andard
    0.12
     foul
    0.12
    Activations Density 0.035%

    No Known Activations