© 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. 15425
    Prev
    Next
    INDEX
    Explanations

    Le Président

    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
    aren
    -0.09
     Mitt
    -0.08
     McM
    -0.07
    <|endoftext|>
    -0.07
     Americ
    -0.07
     practically
    -0.07
     LIS
    -0.07
    <|fim_suffix|>
    -0.06
     Lis
    -0.06
     Kens
    -0.06
    POSITIVE LOGITS
     Michaels
    0.13
    orf
    0.12
    uri
    0.11
     herald
    0.11
     PROVIDED
    0.11
    (PHP
    0.11
     PRES
    0.11
     Shore
    0.11
    osi
    0.11
    styles
    0.11
    Activations Density 0.030%

    No Known Activations