© 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. 89316
    Prev
    Next
    INDEX
    Explanations

    gain weight or moisture

    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
     Twe
    -0.09
     medium
    -0.09
     Stap
    -0.08
    medium
    -0.08
     Medium
    -0.08
    arna
    -0.08
     pled
    -0.08
     READY
    -0.07
     bait
    -0.07
     deb
    -0.07
    POSITIVE LOGITS
     additional
    0.17
    additional
    0.13
    Additional
    0.13
     new
    0.12
    IDO
    0.12
     weight
    0.12
    elo
    0.12
     airs
    0.11
     Additional
    0.11
    new
    0.11
    Activations Density 0.047%

    No Known Activations