© 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. 51010
    Prev
    Next
    INDEX
    Explanations

    navigating or manipulating through obstacles

    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
     periodically
    -0.11
     conclus
    -0.10
    oug
    -0.10
    Ñĥн
    -0.10
    pag
    -0.10
     encount
    -0.10
    atrib
    -0.10
     materially
    -0.09
     realism
    -0.09
     relent
    -0.09
    POSITIVE LOGITS
     maneuver
    0.17
     Mane
    0.16
     maneuvers
    0.13
     tricky
    0.13
     around
    0.12
     positioning
    0.12
     manoe
    0.12
     awkward
    0.12
     clumsy
    0.11
     position
    0.11
    Activations Density 0.017%

    No Known Activations