© 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. 87614
    Prev
    Next
    INDEX
    Explanations

    forcibly acted upon or moved

    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
     kep
    -0.08
    alc
    -0.08
    213
    -0.08
     afin
    -0.08
     kul
    -0.08
     bem
    -0.07
     Meyer
    -0.07
     spr
    -0.07
     using
    -0.07
     reachable
    -0.07
    POSITIVE LOGITS
     rud
    0.14
     apart
    0.13
     away
    0.12
     into
    0.12
     back
    0.11
    rud
    0.11
    BYTES
    0.11
    into
    0.11
     Into
    0.11
     forcibly
    0.11
    Activations Density 0.026%

    No Known Activations