© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46115
    Prev
    Next
    INDEX
    Explanations

    \[ contents

    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
    Negative Logits
     »↵↵
    -0.10
     Daly
    -0.10
     polo
    -0.09
     Sunder
    -0.09
    "struct
    -0.09
    ija
    -0.09
     nack
    -0.08
    :model
    -0.08
    -Allow
    -0.08
    rides
    -0.08
    POSITIVE LOGITS
    +]
    0.15
    CDATA
    0.14
    .]
    0.12
     CIT
    0.12
    adin
    0.11
    ?]
    0.11
    newline
    0.10
     Removed
    0.10
    ...]
    0.10
    emoji
    0.09
    Activations Density 0.109%

    No Known Activations