© 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. 117587
    Prev
    Next
    INDEX
    Explanations

    maneuver or manipulate

    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
     full
    -0.09
    iate
    -0.09
     PARTICULAR
    -0.09
    idon
    -0.09
    xit
    -0.08
     extravag
    -0.08
     Gaz
    -0.08
     Occ
    -0.08
     Hath
    -0.08
     bothered
    -0.08
    POSITIVE LOGITS
     manoe
    0.21
     maneu
    0.21
     maneuver
    0.21
     maneuvers
    0.19
     Mane
    0.15
     manip
    0.12
     mane
    0.12
     Moves
    0.12
     manipulated
    0.11
    uvre
    0.10
    Activations Density 0.001%

    No Known Activations