© 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. 5684
    Prev
    Next
    INDEX
    Explanations

    flesh, disease, people, places

    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
     unb
    -0.12
    acer
    -0.08
    ariat
    -0.08
    rien
    -0.08
    /un
    -0.08
     purge
    -0.08
     pragmatic
    -0.08
     repeatedly
    -0.07
     blow
    -0.07
    ly
    -0.07
    POSITIVE LOGITS
     prefab
    0.12
    inch
    0.10
    ch
    0.10
     ###↵
    0.10
     Bij
    0.10
    oft
    0.09
    mas
    0.09
    937
    0.09
     flakes
    0.09
    markt
    0.09
    Activations Density 0.001%

    No Known Activations