© 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. 29651
    Prev
    Next
    INDEX
    Explanations

    questions starting with "do you"

    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
     Diary
    -0.10
    å¢
    -0.09
     Zag
    -0.09
    umat
    -0.09
     predecess
    -0.09
    <center
    -0.08
     feu
    -0.08
     bols
    -0.08
    _mE
    -0.08
     remix
    -0.08
    POSITIVE LOGITS
    ?
    0.13
     YOUR
    0.13
     wouldn
    0.11
    arton
    0.11
     wonder
    0.11
     yours
    0.11
     you
    0.10
    ?:
    0.10
     intriguing
    0.10
     your
    0.10
    Activations Density 0.089%

    No Known Activations