© 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. 34195
    Prev
    Next
    INDEX
    Explanations

    to the extent

    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
    defs
    -0.11
     prem
    -0.11
     Morales
    -0.10
    itational
    -0.10
    istar
    -0.10
     tooltips
    -0.10
    boo
    -0.09
    insn
    -0.09
     pred
    -0.09
    ugh
    -0.09
    POSITIVE LOGITS
     eyes
    0.11
     surprise
    0.11
     discredit
    0.10
     embarrassment
    0.10
     tune
    0.10
     dismay
    0.10
     credit
    0.09
     eye
    0.09
     touch
    0.09
     regret
    0.09
    Activations Density 0.042%

    No Known Activations