© 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. 46213
    Prev
    Next
    INDEX
    Explanations

    approaching or nearing

    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
     linger
    -0.10
    avis
    -0.10
     adj
    -0.10
     Downs
    -0.10
    dae
    -0.10
     seg
    -0.09
    /www
    -0.09
     outing
    -0.09
     sitting
    -0.09
    oup
    -0.09
    POSITIVE LOGITS
     approaching
    0.48
     Appro
    0.33
     approached
    0.32
    appro
    0.32
    Appro
    0.32
     approach
    0.32
     nearing
    0.31
     approaches
    0.31
     Approach
    0.30
    _appro
    0.29
    Activations Density 0.194%

    No Known Activations