© 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. 48728
    Prev
    Next
    INDEX
    Explanations

    specified number

    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
    exion
    -0.09
     Rep
    -0.09
     gradu
    -0.09
     Voll
    -0.09
    imos
    -0.09
    Dest
    -0.08
     voluntary
    -0.08
    akh
    -0.08
     Suz
    -0.08
    /comments
    -0.08
    POSITIVE LOGITS
     designated
    0.17
     specified
    0.16
     assigned
    0.14
     prescribed
    0.14
     vet
    0.13
     determined
    0.13
     dictated
    0.13
     Mellon
    0.11
     pros
    0.11
     whoever
    0.11
    Activations Density 0.066%

    No Known Activations