© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15555
    Prev
    Next
    INDEX
    Explanations

    already or again

    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
     uncont
    -0.12
     eventually
    -0.12
     Eventually
    -0.10
    rist
    -0.10
     Lawson
    -0.10
     Koch
    -0.10
     Ib
    -0.09
    ìĤ°
    -0.09
    urb
    -0.09
    -cent
    -0.09
    POSITIVE LOGITS
     already
    0.51
     Already
    0.48
    Already
    0.43
    already
    0.40
    å·²
    0.29
     Ñĥже
    0.28
    _already
    0.27
     déjÃł
    0.24
     bereits
    0.21
     prematurely
    0.20
    Activations Density 0.312%

    No Known Activations