© 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. 117329
    Prev
    Next
    INDEX
    Explanations

    yes/no answers

    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
     indeed
    -0.17
     Nope
    -0.16
     untrue
    -0.16
    íķĺì§Ģ
    -0.15
    =false
    -0.14
    FALSE
    -0.14
     nonexistent
    -0.14
    =False
    -0.14
     denies
    -0.14
    Indeed
    -0.13
    POSITIVE LOGITS
     yes
    0.23
     Yes
    0.23
    Yes
    0.20
    "Yes
    0.17
    yes
    0.17
     YES
    0.16
    “Yes
    0.16
    _yes
    0.14
    YES
    0.12
    .Yes
    0.12
    Activations Density 0.090%

    No Known Activations