© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    examples, cases, explanation, functions

    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
     kå
    -0.10
     vidé
    -0.10
    odzi
    -0.09
     terminals
    -0.09
     Janet
    -0.09
    baugh
    -0.09
    rack
    -0.09
    951
    -0.09
    Americ
    -0.09
     lifes
    -0.08
    POSITIVE LOGITS
    posted
    0.10
    ,...↵
    0.09
     Ivy
    0.09
    pag
    0.09
    ...↵
    0.09
     pract
    0.09
    mdi
    0.09
    ECH
    0.09
     MLP
    0.08
    obra
    0.08
    Activations Density 0.005%

    No Known Activations