© 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. 25052
    Prev
    Next
    INDEX
    Explanations

    attached, adhering, or entering

    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
    eri
    -0.11
    assis
    -0.11
     Morr
    -0.10
     owner
    -0.10
    outu
    -0.10
    dae
    -0.10
     mou
    -0.10
     Tune
    -0.09
    ëĭĪ
    -0.09
    caa
    -0.09
    POSITIVE LOGITS
    onto
    0.14
     onto
    0.13
     clinging
    0.11
     Bowman
    0.09
     attached
    0.09
    attached
    0.09
    nad
    0.09
     FOLLOW
    0.09
     Ont
    0.09
     welcoming
    0.09
    Activations Density 0.331%

    No Known Activations