© 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. 26470
    Prev
    Next
    INDEX
    Explanations

    purpose built or designed

    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
     slap
    -0.08
    nga
    -0.08
    orate
    -0.08
     Brig
    -0.08
     Dana
    -0.07
     mounting
    -0.07
     sext
    -0.07
     archives
    -0.07
    ITE
    -0.07
     Whip
    -0.07
    POSITIVE LOGITS
    fully
    0.26
    ful
    0.19
    fulness
    0.18
    -built
    0.15
    lessness
    0.13
    -driven
    0.13
     intent
    0.13
     intention
    0.12
    edly
    0.12
    ively
    0.11
    Activations Density 0.017%

    No Known Activations