© 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. 89164
    Prev
    Next
    INDEX
    Explanations

    power, data, information, processor, file, code

    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
     POV
    -0.09
     incompet
    -0.09
     oceans
    -0.09
    utenberg
    -0.09
     sensed
    -0.09
    cab
    -0.09
    hound
    -0.09
     bunker
    -0.09
     mantle
    -0.08
     Matte
    -0.08
    POSITIVE LOGITS
     rag
    0.12
     harmon
    0.09
     Joi
    0.09
     Malay
    0.09
     Rag
    0.08
     ware
    0.08
    legen
    0.08
     prod
    0.08
    apper
    0.08
    recht
    0.08
    Activations Density 0.001%

    No Known Activations