© 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. 114886
    Prev
    Next
    INDEX
    Explanations

    to see, play, parse, learn, push, eat

    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
     behold
    -0.11
     reportedly
    -0.11
     conclude
    -0.10
     announce
    -0.10
    wap
    -0.09
     duly
    -0.09
     incorporate
    -0.09
     denote
    -0.09
     commence
    -0.09
     capitalize
    -0.09
    POSITIVE LOGITS
    otal
    0.11
    olle
    0.10
    ural
    0.10
    eden
    0.09
     pee
    0.09
     Crab
    0.09
     Hur
    0.09
    ohana
    0.09
    (Box
    0.09
    ula
    0.09
    Activations Density 0.246%

    No Known Activations