© 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. 25164
    Prev
    Next
    INDEX
    Explanations

    scare, shock, terrify

    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
     favor
    -0.09
    237
    -0.09
    ypse
    -0.08
    haar
    -0.08
    ipt
    -0.08
     decre
    -0.08
     dec
    -0.08
     shining
    -0.08
    legen
    -0.08
     dictated
    -0.08
    POSITIVE LOGITS
     awake
    0.17
     into
    0.16
     INTO
    0.14
     away
    0.13
    into
    0.13
     Into
    0.13
     badly
    0.12
     sober
    0.12
    aggi
    0.12
     enough
    0.11
    Activations Density 0.014%

    No Known Activations