© 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. 16230
    Prev
    Next
    INDEX
    Explanations

    e.g., i.e., abbreviations

    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
     Hos
    -0.09
     Morris
    -0.09
    енÑĤ
    -0.08
     Dudley
    -0.08
     courte
    -0.07
     //{↵
    -0.07
     cus
    -0.07
     Yi
    -0.07
     Boyle
    -0.07
    -----↵↵
    -0.07
    POSITIVE LOGITS
    .e
    0.15
     Fancy
    0.13
    .g
    0.12
     smarty
    0.11
    eka
    0.11
    vie
    0.11
    unan
    0.11
    vant
    0.10
    weis
    0.10
     Marr
    0.10
    Activations Density 0.072%

    No Known Activations