© 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. 115919
    Prev
    Next
    INDEX
    Explanations

    Sun Pharma

    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
     ...↵
    -0.13
    <|endoftext|>
    -0.12
     ...↵↵
    -0.12
    ...↵
    -0.12
    ↵↵↵↵↵↵
    -0.11
    âĢ¦↵
    -0.10
     -↵
    -0.10
     :↵
    -0.10
    ...↵↵
    -0.10
    ...↵↵↵
    -0.09
    POSITIVE LOGITS
     Riv
    0.10
    aeda
    0.09
    Ĝ
    0.09
     riv
    0.09
     :+:
    0.09
     Skinny
    0.09
     bow
    0.08
    ”ãĢĤ↵↵
    0.08
     Fucked
    0.08
     sce
    0.08
    Activations Density 0.032%

    No Known Activations