© 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. 91678
    Prev
    Next
    INDEX
    Explanations

    positions, platforms, or contours

    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
    DVD
    -0.10
    grab
    -0.10
     Kris
    -0.09
    KD
    -0.09
    atty
    -0.09
     bib
    -0.09
     outr
    -0.08
     Bib
    -0.08
    alone
    -0.08
     Mer
    -0.08
    POSITIVE LOGITS
     closer
    0.21
     tighter
    0.18
     nearer
    0.14
     deeper
    0.14
     harder
    0.13
     tightly
    0.12
     tight
    0.12
     easier
    0.11
     farther
    0.11
     tightened
    0.11
    Activations Density 0.018%

    No Known Activations