© 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. 3907
    Prev
    Next
    INDEX
    Explanations

    posting or publishing content

    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
    oma
    -0.12
    <|endoftext|>
    -0.12
    ispers
    -0.11
     Verd
    -0.11
     Caldwell
    -0.11
    âĢ¦↵↵↵↵
    -0.11
     pii
    -0.11
    .↵↵↵↵↵↵↵↵↵↵↵↵
    -0.10
     scratched
    -0.10
    <|fim_prefix|>
    -0.10
    POSITIVE LOGITS
    Posted
    0.25
     Posted
    0.23
     posted
    0.20
    posted
    0.18
     Published
    0.13
    Submitted
    0.13
     published
    0.12
    Published
    0.12
     Submitted
    0.11
     admin
    0.11
    Activations Density 0.418%

    No Known Activations