© 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. 16315
    Prev
    Next
    INDEX
    Explanations

    describes how they

    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
     Vu
    -0.08
     medi
    -0.07
     Wr
    -0.07
    atra
    -0.07
    tra
    -0.07
     Northwestern
    -0.07
     Peach
    -0.07
    .defaults
    -0.07
     saf
    -0.07
     Trio
    -0.07
    POSITIVE LOGITS
     occur
    0.16
     occurred
    0.15
     occurs
    0.14
    Occurs
    0.14
     occurring
    0.14
     happen
    0.12
     arisen
    0.12
     flowed
    0.12
     happening
    0.12
     perme
    0.12
    Activations Density 0.646%

    No Known Activations