© 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. 114961
    Prev
    Next
    INDEX
    Explanations

    Latvians, Clostridium, Streptococcus, Shigella

    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
     enc
    -0.08
    mens
    -0.08
     Salmon
    -0.08
    laus
    -0.08
    cer
    -0.08
    omens
    -0.08
    otten
    -0.07
    viso
    -0.07
     mortal
    -0.07
    saving
    -0.07
    POSITIVE LOGITS
    unde
    0.09
     justo
    0.08
    immer
    0.08
    tele
    0.08
    .ReadAll
    0.08
     Panc
    0.08
    steel
    0.08
    bum
    0.08
     Scotia
    0.08
     Stateless
    0.08
    Activations Density 1.387%

    No Known Activations