© 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. 87603
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
     Hood
    -0.12
     lineage
    -0.11
     hood
    -0.11
     synerg
    -0.10
    /state
    -0.10
     mirac
    -0.10
    hood
    -0.10
     firsthand
    -0.10
    /gif
    -0.10
     Consort
    -0.10
    POSITIVE LOGITS
     question
    0.19
     Question
    0.16
     QUESTION
    0.14
    question
    0.14
    (question
    0.12
    -question
    0.12
    _question
    0.11
    /question
    0.11
    Question
    0.11
     hypothetical
    0.11
    Activations Density 0.072%

    No Known Activations