© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5692
    Prev
    Next
    INDEX
    Explanations

    force or powerful entities/effects

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Vill
    -0.10
    iran
    -0.10
     tastes
    -0.09
     Vaughan
    -0.09
    ahr
    -0.09
     discret
    -0.09
     bribery
    -0.09
     provoc
    -0.09
     sticks
    -0.09
     Huss
    -0.09
    POSITIVE LOGITS
     force
    0.23
     thrust
    0.18
    -force
    0.17
     recoil
    0.16
     pushes
    0.16
    force
    0.15
     forces
    0.15
     shove
    0.14
     Force
    0.14
     blow
    0.14
    Activations Density 0.050%

    No Known Activations