© 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. 90022
    Prev
    Next
    INDEX
    Explanations

    microbiota or gut flora

    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
    æľį
    -0.11
     wr
    -0.10
     trib
    -0.10
     Conn
    -0.09
     Occupation
    -0.09
    wert
    -0.09
     dung
    -0.09
    gre
    -0.09
    istor
    -0.09
    danger
    -0.09
    POSITIVE LOGITS
     grooming
    0.09
    #aa
    0.08
     groom
    0.08
    iffe
    0.08
    onto
    0.08
    abay
    0.08
     asym
    0.07
    lands
    0.07
     Treasure
    0.07
     conserv
    0.07
    Activations Density 0.005%

    No Known Activations