© 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. 92458
    Prev
    Next
    INDEX
    Explanations

    import/fuels/Jesus/boost/jury

    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
     Harr
    -0.11
    rega
    -0.09
     Bol
    -0.09
     bol
    -0.09
     outr
    -0.09
    -library
    -0.09
    edd
    -0.09
     Cyr
    -0.09
    oha
    -0.09
    bol
    -0.09
    POSITIVE LOGITS
     access
    0.12
     inviting
    0.12
     gladly
    0.11
     alto
    0.10
     gesture
    0.10
     willingly
    0.10
     anticipated
    0.10
    994
    0.10
    fal
    0.10
     easier
    0.09
    Activations Density 0.032%

    No Known Activations