© 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. 117330
    Prev
    Next
    INDEX
    Explanations

    leave a comment or reply

    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
     Gerard
    -0.09
     GK
    -0.08
    alm
    -0.08
     Pierre
    -0.08
    Wire
    -0.08
    fts
    -0.08
     Boom
    -0.07
     hands
    -0.07
    Boom
    -0.07
     Carm
    -0.07
    POSITIVE LOGITS
     нап
    0.12
     Comment
    0.12
     comment
    0.12
     reply
    0.11
     COMMENTS
    0.11
    SqlConnection
    0.11
     comments
    0.11
    ,eg
    0.11
    tti
    0.11
    çīĩ
    0.10
    Activations Density 0.001%

    No Known Activations