© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    in the context of moving 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
    gor
    -0.10
    ivre
    -0.10
     Forward
    -0.10
    argon
    -0.09
     lingering
    -0.09
    antis
    -0.09
     forward
    -0.09
    isce
    -0.09
    Forward
    -0.08
    ant
    -0.08
    POSITIVE LOGITS
    /out
    0.18
    wards
    0.17
     into
    0.14
    _into
    0.12
     vÃło
    0.11
     reflexivity
    0.10
     hart
    0.10
    animate
    0.10
    Into
    0.10
    opsis
    0.09
    Activations Density 0.263%

    No Known Activations