© 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. 111719
    Prev
    Next
    INDEX
    Explanations

    formulating questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     requesting
    -0.12
     Dorm
    -0.11
     Chatt
    -0.11
    interpreted
    -0.10
     suspects
    -0.10
    747
    -0.10
     suspect
    -0.10
    Cad
    -0.10
     Favorite
    -0.10
     mentioning
    -0.10
    POSITIVE LOGITS
     question
    0.24
     questions
    0.21
     answered
    0.21
     unanswered
    0.19
     answering
    0.18
     answer
    0.16
     Questions
    0.15
     answers
    0.15
    answered
    0.15
    question
    0.15
    Activations Density 0.240%

    No Known Activations