© 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. 47663
    Prev
    Next
    INDEX
    Explanations

    there is/are

    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
    kker
    -0.11
     Bes
    -0.10
     dispar
    -0.10
     Dud
    -0.09
    gle
    -0.09
    gba
    -0.09
     acqu
    -0.09
     Reward
    -0.09
     rewarding
    -0.09
     consequential
    -0.09
    POSITIVE LOGITS
     Sight
    0.09
     noticeable
    0.09
     ports
    0.09
     sight
    0.09
     visible
    0.09
     instructions
    0.08
     NOTICE
    0.08
     Ports
    0.08
     Griffith
    0.08
     fore
    0.08
    Activations Density 0.041%

    No Known Activations