© 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. 87898
    Prev
    Next
    INDEX
    Explanations

    please let us not

    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
     Aren
    -0.11
    xo
    -0.09
    resh
    -0.08
     cal
    -0.08
    IDA
    -0.08
     isnt
    -0.08
    /reference
    -0.08
     Cla
    -0.08
    ongs
    -0.08
     Ott
    -0.08
    POSITIVE LOGITS
     DON
    0.20
     please
    0.19
     PLEASE
    0.18
     DO
    0.18
     NEVER
    0.17
     avoid
    0.17
     don
    0.17
    please
    0.16
     Definitely
    0.16
     Please
    0.14
    Activations Density 0.062%

    No Known Activations