© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113756
    Prev
    Next
    INDEX
    Explanations

    football, right, Pokémon, MySQL, 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
    (er
    -0.08
     priv
    -0.08
     ceremon
    -0.08
    uros
    -0.07
     spo
    -0.07
     Serie
    -0.07
    /pre
    -0.07
     bron
    -0.07
     pron
    -0.07
     stere
    -0.07
    POSITIVE LOGITS
    ulle
    0.11
    nel
    0.10
    /avatar
    0.10
    iese
    0.10
     immedi
    0.10
     Appalachian
    0.10
    oload
    0.10
     Gothic
    0.10
     Koch
    0.10
    ivy
    0.10
    Activations Density 0.001%

    No Known Activations