© 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. 6210
    Prev
    Next
    INDEX
    Explanations

    lists of services or topics

    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
    <|fim_suffix|>
    -0.10
     evid
    -0.10
     only
    -0.10
    Gratis
    -0.10
     fundament
    -0.10
     frail
    -0.09
     evidenced
    -0.09
     equally
    -0.09
     here
    -0.09
    Porn
    -0.09
    POSITIVE LOGITS
     etc
    0.31
    etc
    0.23
     ...)
    0.13
     various
    0.10
     sowie
    0.10
     ...)↵
    0.09
    /or
    0.09
    /etc
    0.09
     ....↵↵
    0.08
     ?,
    0.08
    Activations Density 0.625%

    No Known Activations