© 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. 31713
    Prev
    Next
    INDEX
    Explanations

    specifically designed or intended

    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
     particular
    -0.10
    (er
    -0.10
    ser
    -0.10
     particul
    -0.10
    cts
    -0.10
    izers
    -0.10
     specific
    -0.09
    leg
    -0.09
     Specific
    -0.09
    IZE
    -0.09
    POSITIVE LOGITS
     designed
    0.18
     tailored
    0.16
    -designed
    0.13
     Designed
    0.13
    Designed
    0.11
     formulated
    0.11
     crafted
    0.11
     tailor
    0.10
     targeting
    0.10
     adapted
    0.10
    Activations Density 0.032%

    No Known Activations