© 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. 34017
    Prev
    Next
    INDEX
    Explanations

    movement into or out of locations

    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
    é¦
    -0.11
     entering
    -0.10
     enter
    -0.10
    shortcut
    -0.10
    aben
    -0.10
     shortcut
    -0.10
     entrar
    -0.10
    eco
    -0.09
     hurry
    -0.09
    Enter
    -0.09
    POSITIVE LOGITS
     upstairs
    0.16
     downstairs
    0.15
     outside
    0.12
     nack
    0.11
     closer
    0.10
    outside
    0.10
     Outside
    0.10
     inside
    0.09
     fora
    0.09
     thr
    0.09
    Activations Density 0.064%

    No Known Activations