© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    shocked or stunned reactions

    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
     tightly
    -0.10
    iren
    -0.10
    esto
    -0.09
     Phoenix
    -0.09
     touches
    -0.09
    çIJĨ
    -0.09
     tighten
    -0.09
     consts
    -0.09
    UTION
    -0.09
    coded
    -0.09
    POSITIVE LOGITS
    ingly
    0.17
     shock
    0.14
     disbelief
    0.13
     stun
    0.13
     Shock
    0.13
     silence
    0.12
    waves
    0.12
     shocks
    0.11
     revelations
    0.11
    Shock
    0.11
    Activations Density 0.020%

    No Known Activations