© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    you can have need should

    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
     foresee
    -0.10
    vd
    -0.10
     insist
    -0.09
     preset
    -0.09
     insists
    -0.09
     whereby
    -0.09
    fork
    -0.08
     laz
    -0.08
     alternatively
    -0.08
     centrally
    -0.08
    POSITIVE LOGITS
     shouldn
    0.20
     cannot
    0.16
     should
    0.15
     Cannot
    0.13
     Should
    0.13
     NEED
    0.12
    usu
    0.12
     need
    0.12
     needs
    0.12
     SHOULD
    0.11
    Activations Density 0.075%

    No Known Activations