© 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. 8302
    Prev
    Next
    INDEX
    Explanations

    need to + verb

    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
     pity
    -0.13
    wie
    -0.12
    935
    -0.12
     beware
    -0.12
     gratuit
    -0.11
     diplom
    -0.11
    oct
    -0.10
    oud
    -0.10
    reib
    -0.10
    704
    -0.10
    POSITIVE LOGITS
     borrow
    0.18
    borrow
    0.15
     Borrow
    0.15
     borrowing
    0.13
     borrowed
    0.13
     know
    0.11
     bor
    0.10
     Know
    0.10
     access
    0.09
     discussed
    0.08
    Activations Density 0.106%

    No Known Activations