© 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. 18764
    Prev
    Next
    INDEX
    Explanations

    until

    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
     CPR
    -0.11
    onet
    -0.11
    ally
    -0.10
    edata
    -0.10
     nowhere
    -0.10
    quo
    -0.10
    ëĵ
    -0.10
    ê¸Ģ
    -0.10
    elog
    -0.09
     bre
    -0.09
    POSITIVE LOGITS
    /if
    0.12
     they
    0.11
     numb
    0.10
    lei
    0.09
     instructed
    0.09
     ready
    0.09
    /un
    0.09
     hunger
    0.08
     circumstances
    0.08
     dawn
    0.08
    Activations Density 0.015%

    No Known Activations